SoulInPsyAbstract commited on
Commit
befbb25
·
verified ·
1 Parent(s): d1726ee

Upload folder using huggingface_hub

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .gitattributes +6 -0
  2. README.md +209 -0
  3. adapter_config.json +50 -0
  4. adapter_model.safetensors +3 -0
  5. checkpoint-200/README.md +209 -0
  6. checkpoint-200/adapter_config.json +50 -0
  7. checkpoint-200/adapter_model.safetensors +3 -0
  8. checkpoint-200/optimizer.pt +3 -0
  9. checkpoint-200/rng_state.pth +3 -0
  10. checkpoint-200/scheduler.pt +3 -0
  11. checkpoint-200/special_tokens_map.json +17 -0
  12. checkpoint-200/tokenizer.json +3 -0
  13. checkpoint-200/tokenizer_config.json +2072 -0
  14. checkpoint-200/trainer_state.json +393 -0
  15. checkpoint-200/training_args.bin +3 -0
  16. checkpoint-400/README.md +209 -0
  17. checkpoint-400/adapter_config.json +50 -0
  18. checkpoint-400/adapter_model.safetensors +3 -0
  19. checkpoint-400/optimizer.pt +3 -0
  20. checkpoint-400/rng_state.pth +3 -0
  21. checkpoint-400/scheduler.pt +3 -0
  22. checkpoint-400/special_tokens_map.json +17 -0
  23. checkpoint-400/tokenizer.json +3 -0
  24. checkpoint-400/tokenizer_config.json +2072 -0
  25. checkpoint-400/trainer_state.json +753 -0
  26. checkpoint-400/training_args.bin +3 -0
  27. checkpoint-600/README.md +209 -0
  28. checkpoint-600/adapter_config.json +50 -0
  29. checkpoint-600/adapter_model.safetensors +3 -0
  30. checkpoint-600/optimizer.pt +3 -0
  31. checkpoint-600/rng_state.pth +3 -0
  32. checkpoint-600/scheduler.pt +3 -0
  33. checkpoint-600/special_tokens_map.json +17 -0
  34. checkpoint-600/tokenizer.json +3 -0
  35. checkpoint-600/tokenizer_config.json +2072 -0
  36. checkpoint-600/trainer_state.json +1113 -0
  37. checkpoint-600/training_args.bin +3 -0
  38. checkpoint-800/README.md +209 -0
  39. checkpoint-800/adapter_config.json +50 -0
  40. checkpoint-800/adapter_model.safetensors +3 -0
  41. checkpoint-800/optimizer.pt +3 -0
  42. checkpoint-800/rng_state.pth +3 -0
  43. checkpoint-800/scheduler.pt +3 -0
  44. checkpoint-800/special_tokens_map.json +17 -0
  45. checkpoint-800/tokenizer.json +3 -0
  46. checkpoint-800/tokenizer_config.json +2072 -0
  47. checkpoint-800/trainer_state.json +1473 -0
  48. checkpoint-800/training_args.bin +3 -0
  49. checkpoint-879/README.md +209 -0
  50. checkpoint-879/adapter_config.json +50 -0
.gitattributes CHANGED
@@ -33,3 +33,9 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ checkpoint-200/tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
+ checkpoint-400/tokenizer.json filter=lfs diff=lfs merge=lfs -text
38
+ checkpoint-600/tokenizer.json filter=lfs diff=lfs merge=lfs -text
39
+ checkpoint-800/tokenizer.json filter=lfs diff=lfs merge=lfs -text
40
+ checkpoint-879/tokenizer.json filter=lfs diff=lfs merge=lfs -text
41
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,209 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: NousResearch/Hermes-3-Llama-3.1-8B
3
+ library_name: peft
4
+ pipeline_tag: text-generation
5
+ tags:
6
+ - base_model:adapter:NousResearch/Hermes-3-Llama-3.1-8B
7
+ - lora
8
+ - sft
9
+ - transformers
10
+ - trl
11
+ ---
12
+
13
+ # Model Card for Model ID
14
+
15
+ <!-- Provide a quick summary of what the model is/does. -->
16
+
17
+
18
+
19
+ ## Model Details
20
+
21
+ ### Model Description
22
+
23
+ <!-- Provide a longer summary of what this model is. -->
24
+
25
+
26
+
27
+ - **Developed by:** [More Information Needed]
28
+ - **Funded by [optional]:** [More Information Needed]
29
+ - **Shared by [optional]:** [More Information Needed]
30
+ - **Model type:** [More Information Needed]
31
+ - **Language(s) (NLP):** [More Information Needed]
32
+ - **License:** [More Information Needed]
33
+ - **Finetuned from model [optional]:** [More Information Needed]
34
+
35
+ ### Model Sources [optional]
36
+
37
+ <!-- Provide the basic links for the model. -->
38
+
39
+ - **Repository:** [More Information Needed]
40
+ - **Paper [optional]:** [More Information Needed]
41
+ - **Demo [optional]:** [More Information Needed]
42
+
43
+ ## Uses
44
+
45
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
46
+
47
+ ### Direct Use
48
+
49
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
50
+
51
+ [More Information Needed]
52
+
53
+ ### Downstream Use [optional]
54
+
55
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
56
+
57
+ [More Information Needed]
58
+
59
+ ### Out-of-Scope Use
60
+
61
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
62
+
63
+ [More Information Needed]
64
+
65
+ ## Bias, Risks, and Limitations
66
+
67
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
68
+
69
+ [More Information Needed]
70
+
71
+ ### Recommendations
72
+
73
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
74
+
75
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
76
+
77
+ ## How to Get Started with the Model
78
+
79
+ Use the code below to get started with the model.
80
+
81
+ [More Information Needed]
82
+
83
+ ## Training Details
84
+
85
+ ### Training Data
86
+
87
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
88
+
89
+ [More Information Needed]
90
+
91
+ ### Training Procedure
92
+
93
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
94
+
95
+ #### Preprocessing [optional]
96
+
97
+ [More Information Needed]
98
+
99
+
100
+ #### Training Hyperparameters
101
+
102
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
103
+
104
+ #### Speeds, Sizes, Times [optional]
105
+
106
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
107
+
108
+ [More Information Needed]
109
+
110
+ ## Evaluation
111
+
112
+ <!-- This section describes the evaluation protocols and provides the results. -->
113
+
114
+ ### Testing Data, Factors & Metrics
115
+
116
+ #### Testing Data
117
+
118
+ <!-- This should link to a Dataset Card if possible. -->
119
+
120
+ [More Information Needed]
121
+
122
+ #### Factors
123
+
124
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
125
+
126
+ [More Information Needed]
127
+
128
+ #### Metrics
129
+
130
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
131
+
132
+ [More Information Needed]
133
+
134
+ ### Results
135
+
136
+ [More Information Needed]
137
+
138
+ #### Summary
139
+
140
+
141
+
142
+ ## Model Examination [optional]
143
+
144
+ <!-- Relevant interpretability work for the model goes here -->
145
+
146
+ [More Information Needed]
147
+
148
+ ## Environmental Impact
149
+
150
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
151
+
152
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
153
+
154
+ - **Hardware Type:** [More Information Needed]
155
+ - **Hours used:** [More Information Needed]
156
+ - **Cloud Provider:** [More Information Needed]
157
+ - **Compute Region:** [More Information Needed]
158
+ - **Carbon Emitted:** [More Information Needed]
159
+
160
+ ## Technical Specifications [optional]
161
+
162
+ ### Model Architecture and Objective
163
+
164
+ [More Information Needed]
165
+
166
+ ### Compute Infrastructure
167
+
168
+ [More Information Needed]
169
+
170
+ #### Hardware
171
+
172
+ [More Information Needed]
173
+
174
+ #### Software
175
+
176
+ [More Information Needed]
177
+
178
+ ## Citation [optional]
179
+
180
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
181
+
182
+ **BibTeX:**
183
+
184
+ [More Information Needed]
185
+
186
+ **APA:**
187
+
188
+ [More Information Needed]
189
+
190
+ ## Glossary [optional]
191
+
192
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
193
+
194
+ [More Information Needed]
195
+
196
+ ## More Information [optional]
197
+
198
+ [More Information Needed]
199
+
200
+ ## Model Card Authors [optional]
201
+
202
+ [More Information Needed]
203
+
204
+ ## Model Card Contact
205
+
206
+ [More Information Needed]
207
+ ### Framework versions
208
+
209
+ - PEFT 0.20.0
adapter_config.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alora_invocation_tokens": null,
3
+ "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": null,
6
+ "base_model_name_or_path": "NousResearch/Hermes-3-Llama-3.1-8B",
7
+ "bias": "none",
8
+ "corda_config": null,
9
+ "ensure_weight_tying": false,
10
+ "eva_config": null,
11
+ "exclude_modules": null,
12
+ "fan_in_fan_out": false,
13
+ "inference_mode": true,
14
+ "init_lora_weights": true,
15
+ "layer_replication": null,
16
+ "layers_pattern": null,
17
+ "layers_to_transform": null,
18
+ "loftq_config": {},
19
+ "lora_alpha": 32,
20
+ "lora_bias": false,
21
+ "lora_dropout": 0.05,
22
+ "lora_ga_config": null,
23
+ "megatron_config": null,
24
+ "megatron_core": "megatron.core",
25
+ "modules_to_save": null,
26
+ "monteclora_config": null,
27
+ "peft_type": "LORA",
28
+ "peft_version": "0.20.0",
29
+ "qalora_group_size": 16,
30
+ "r": 16,
31
+ "rank_pattern": {},
32
+ "revision": null,
33
+ "target_modules": [
34
+ "v_proj",
35
+ "q_proj",
36
+ "k_proj",
37
+ "down_proj",
38
+ "up_proj",
39
+ "gate_proj",
40
+ "o_proj"
41
+ ],
42
+ "target_parameters": null,
43
+ "task_type": "CAUSAL_LM",
44
+ "trainable_token_indices": null,
45
+ "use_bdlora": null,
46
+ "use_dora": false,
47
+ "use_qalora": false,
48
+ "use_rslora": false,
49
+ "velora_config": null
50
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ac73482dab07a18e9416036be9875bd9965b5fbb11900b7e33bf7618fb628c6
3
+ size 167832240
checkpoint-200/README.md ADDED
@@ -0,0 +1,209 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: NousResearch/Hermes-3-Llama-3.1-8B
3
+ library_name: peft
4
+ pipeline_tag: text-generation
5
+ tags:
6
+ - base_model:adapter:NousResearch/Hermes-3-Llama-3.1-8B
7
+ - lora
8
+ - sft
9
+ - transformers
10
+ - trl
11
+ ---
12
+
13
+ # Model Card for Model ID
14
+
15
+ <!-- Provide a quick summary of what the model is/does. -->
16
+
17
+
18
+
19
+ ## Model Details
20
+
21
+ ### Model Description
22
+
23
+ <!-- Provide a longer summary of what this model is. -->
24
+
25
+
26
+
27
+ - **Developed by:** [More Information Needed]
28
+ - **Funded by [optional]:** [More Information Needed]
29
+ - **Shared by [optional]:** [More Information Needed]
30
+ - **Model type:** [More Information Needed]
31
+ - **Language(s) (NLP):** [More Information Needed]
32
+ - **License:** [More Information Needed]
33
+ - **Finetuned from model [optional]:** [More Information Needed]
34
+
35
+ ### Model Sources [optional]
36
+
37
+ <!-- Provide the basic links for the model. -->
38
+
39
+ - **Repository:** [More Information Needed]
40
+ - **Paper [optional]:** [More Information Needed]
41
+ - **Demo [optional]:** [More Information Needed]
42
+
43
+ ## Uses
44
+
45
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
46
+
47
+ ### Direct Use
48
+
49
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
50
+
51
+ [More Information Needed]
52
+
53
+ ### Downstream Use [optional]
54
+
55
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
56
+
57
+ [More Information Needed]
58
+
59
+ ### Out-of-Scope Use
60
+
61
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
62
+
63
+ [More Information Needed]
64
+
65
+ ## Bias, Risks, and Limitations
66
+
67
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
68
+
69
+ [More Information Needed]
70
+
71
+ ### Recommendations
72
+
73
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
74
+
75
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
76
+
77
+ ## How to Get Started with the Model
78
+
79
+ Use the code below to get started with the model.
80
+
81
+ [More Information Needed]
82
+
83
+ ## Training Details
84
+
85
+ ### Training Data
86
+
87
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
88
+
89
+ [More Information Needed]
90
+
91
+ ### Training Procedure
92
+
93
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
94
+
95
+ #### Preprocessing [optional]
96
+
97
+ [More Information Needed]
98
+
99
+
100
+ #### Training Hyperparameters
101
+
102
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
103
+
104
+ #### Speeds, Sizes, Times [optional]
105
+
106
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
107
+
108
+ [More Information Needed]
109
+
110
+ ## Evaluation
111
+
112
+ <!-- This section describes the evaluation protocols and provides the results. -->
113
+
114
+ ### Testing Data, Factors & Metrics
115
+
116
+ #### Testing Data
117
+
118
+ <!-- This should link to a Dataset Card if possible. -->
119
+
120
+ [More Information Needed]
121
+
122
+ #### Factors
123
+
124
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
125
+
126
+ [More Information Needed]
127
+
128
+ #### Metrics
129
+
130
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
131
+
132
+ [More Information Needed]
133
+
134
+ ### Results
135
+
136
+ [More Information Needed]
137
+
138
+ #### Summary
139
+
140
+
141
+
142
+ ## Model Examination [optional]
143
+
144
+ <!-- Relevant interpretability work for the model goes here -->
145
+
146
+ [More Information Needed]
147
+
148
+ ## Environmental Impact
149
+
150
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
151
+
152
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
153
+
154
+ - **Hardware Type:** [More Information Needed]
155
+ - **Hours used:** [More Information Needed]
156
+ - **Cloud Provider:** [More Information Needed]
157
+ - **Compute Region:** [More Information Needed]
158
+ - **Carbon Emitted:** [More Information Needed]
159
+
160
+ ## Technical Specifications [optional]
161
+
162
+ ### Model Architecture and Objective
163
+
164
+ [More Information Needed]
165
+
166
+ ### Compute Infrastructure
167
+
168
+ [More Information Needed]
169
+
170
+ #### Hardware
171
+
172
+ [More Information Needed]
173
+
174
+ #### Software
175
+
176
+ [More Information Needed]
177
+
178
+ ## Citation [optional]
179
+
180
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
181
+
182
+ **BibTeX:**
183
+
184
+ [More Information Needed]
185
+
186
+ **APA:**
187
+
188
+ [More Information Needed]
189
+
190
+ ## Glossary [optional]
191
+
192
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
193
+
194
+ [More Information Needed]
195
+
196
+ ## More Information [optional]
197
+
198
+ [More Information Needed]
199
+
200
+ ## Model Card Authors [optional]
201
+
202
+ [More Information Needed]
203
+
204
+ ## Model Card Contact
205
+
206
+ [More Information Needed]
207
+ ### Framework versions
208
+
209
+ - PEFT 0.20.0
checkpoint-200/adapter_config.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alora_invocation_tokens": null,
3
+ "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": null,
6
+ "base_model_name_or_path": "NousResearch/Hermes-3-Llama-3.1-8B",
7
+ "bias": "none",
8
+ "corda_config": null,
9
+ "ensure_weight_tying": false,
10
+ "eva_config": null,
11
+ "exclude_modules": null,
12
+ "fan_in_fan_out": false,
13
+ "inference_mode": true,
14
+ "init_lora_weights": true,
15
+ "layer_replication": null,
16
+ "layers_pattern": null,
17
+ "layers_to_transform": null,
18
+ "loftq_config": {},
19
+ "lora_alpha": 32,
20
+ "lora_bias": false,
21
+ "lora_dropout": 0.05,
22
+ "lora_ga_config": null,
23
+ "megatron_config": null,
24
+ "megatron_core": "megatron.core",
25
+ "modules_to_save": null,
26
+ "monteclora_config": null,
27
+ "peft_type": "LORA",
28
+ "peft_version": "0.20.0",
29
+ "qalora_group_size": 16,
30
+ "r": 16,
31
+ "rank_pattern": {},
32
+ "revision": null,
33
+ "target_modules": [
34
+ "v_proj",
35
+ "q_proj",
36
+ "k_proj",
37
+ "down_proj",
38
+ "up_proj",
39
+ "gate_proj",
40
+ "o_proj"
41
+ ],
42
+ "target_parameters": null,
43
+ "task_type": "CAUSAL_LM",
44
+ "trainable_token_indices": null,
45
+ "use_bdlora": null,
46
+ "use_dora": false,
47
+ "use_qalora": false,
48
+ "use_rslora": false,
49
+ "velora_config": null
50
+ }
checkpoint-200/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03d405e3ae88fa2813a3ee78b66a7a0c5e03e899611495ab2506fa1f7ed9dfea
3
+ size 167832240
checkpoint-200/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eaa64d2cf898f55baeac5c8c3c99474f4a91c6c937ef8817baf4e9eadbb6b45e
3
+ size 85727828
checkpoint-200/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f39589146f58675d323c28a7637c2b197c2470f377bdc1b580174509beea1240
3
+ size 14244
checkpoint-200/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f0a841d0fa965ade7dbf3a34a1021756a215f73311c59e711208417d012e806
3
+ size 1064
checkpoint-200/special_tokens_map.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|im_end|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|im_end|>"
17
+ }
checkpoint-200/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14b5e679cb69af62e14c3b98d346177bd4137d882a44f87dec9efec982b01a05
3
+ size 17209403
checkpoint-200/tokenizer_config.json ADDED
@@ -0,0 +1,2072 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<tool_call>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": false
26
+ },
27
+ "128003": {
28
+ "content": "<tool_response>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": false
34
+ },
35
+ "128004": {
36
+ "content": "<|finetune_right_pad_id|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_2|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128006": {
52
+ "content": "<|start_header_id|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "128007": {
60
+ "content": "<|end_header_id|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "128008": {
68
+ "content": "<|eom_id|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "128009": {
76
+ "content": "<|eot_id|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "128010": {
84
+ "content": "<|python_tag|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<tools>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": false
98
+ },
99
+ "128012": {
100
+ "content": "</tools>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": false
106
+ },
107
+ "128013": {
108
+ "content": "</tool_call>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": false
114
+ },
115
+ "128014": {
116
+ "content": "</tool_response>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": false
122
+ },
123
+ "128015": {
124
+ "content": "<schema>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": false
130
+ },
131
+ "128016": {
132
+ "content": "</schema>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": false
138
+ },
139
+ "128017": {
140
+ "content": "<scratch_pad>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": false
146
+ },
147
+ "128018": {
148
+ "content": "</scratch_pad>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": false
154
+ },
155
+ "128019": {
156
+ "content": "<SCRATCHPAD>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": false
162
+ },
163
+ "128020": {
164
+ "content": "</SCRATCHPAD>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": false
170
+ },
171
+ "128021": {
172
+ "content": "<REASONING>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": false
178
+ },
179
+ "128022": {
180
+ "content": "</REASONING>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": false
186
+ },
187
+ "128023": {
188
+ "content": "<INNER_MONOLOGUE>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": false
194
+ },
195
+ "128024": {
196
+ "content": "</INNER_MONOLOGUE>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": false
202
+ },
203
+ "128025": {
204
+ "content": "<PLAN>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": false
210
+ },
211
+ "128026": {
212
+ "content": "</PLAN>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": false
218
+ },
219
+ "128027": {
220
+ "content": "<EXECUTION>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": false
226
+ },
227
+ "128028": {
228
+ "content": "</EXECUTION>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": false
234
+ },
235
+ "128029": {
236
+ "content": "<REFLECTION>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": false
242
+ },
243
+ "128030": {
244
+ "content": "</REFLECTION>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": false
250
+ },
251
+ "128031": {
252
+ "content": "<THINKING>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": false
258
+ },
259
+ "128032": {
260
+ "content": "</THINKING>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": false
266
+ },
267
+ "128033": {
268
+ "content": "<SOLUTION>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": false
274
+ },
275
+ "128034": {
276
+ "content": "</SOLUTION>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": false
282
+ },
283
+ "128035": {
284
+ "content": "<EXPLANATION>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": false
290
+ },
291
+ "128036": {
292
+ "content": "</EXPLANATION>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": false
298
+ },
299
+ "128037": {
300
+ "content": "<UNIT_TEST>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": false
306
+ },
307
+ "128038": {
308
+ "content": "</UNIT_TEST>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": false
314
+ },
315
+ "128039": {
316
+ "content": "<|im_start|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": false
322
+ },
323
+ "128040": {
324
+ "content": "<|im_end|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_33|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_34|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_35|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_36|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_37|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_38|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_39|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_40|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_41|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_42|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_43|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_44|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_45|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_46|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_47|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_48|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_49|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_50|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_51|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_52|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_53|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_54|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_55|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_56|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_57|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_58|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_59|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_60|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_61|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_62|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_63|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_64|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_65|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_66|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_67|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_68|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_69|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_70|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_71|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_72|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_73|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_74|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_75|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_76|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_77|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_78|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_79|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_80|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_81|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_82|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_83|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_84|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_85|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_86|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_87|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_88|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_89|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_90|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_91|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_92|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_93|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_94|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_95|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_96|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_97|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_98|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_99|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_100|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_101|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_102|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_103|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_104|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_105|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_106|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_107|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_108|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_109|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_110|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_111|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_112|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_113|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_114|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_115|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_116|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_117|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_118|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_119|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_120|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_121|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_122|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_123|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_124|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_125|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_126|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_127|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_128|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_129|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_130|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_131|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_132|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_133|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_134|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_135|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_136|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_137|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_138|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_139|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_140|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_141|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_142|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_143|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_144|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_145|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_146|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_147|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_148|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_149|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_150|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_151|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_152|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_153|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_154|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_155|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_156|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_157|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_158|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_159|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_160|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_161|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_162|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_163|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_164|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_165|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_166|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_167|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_168|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_169|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_170|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_171|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_172|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_173|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_174|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_175|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_176|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_177|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_178|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_179|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_180|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_181|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_182|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_183|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_184|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_185|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_186|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_187|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_188|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_189|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_190|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_191|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_192|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_193|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_194|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_195|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_196|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_197|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_198|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_199|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_200|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_201|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_202|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_203|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_204|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_205|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_206|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_207|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_208|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_209|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_210|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_211|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_212|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_213|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_214|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_215|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_216|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_217|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_218|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_219|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_220|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_221|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_222|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_223|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_224|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_225|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_226|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_227|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_228|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_229|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_230|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_231|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_232|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_233|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_234|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_235|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_236|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_237|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_238|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_239|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_240|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_241|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_242|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_243|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_244|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_245|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_246|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_247|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ }
2051
+ },
2052
+ "bos_token": "<|begin_of_text|>",
2053
+ "chat_template": [
2054
+ {
2055
+ "name": "default",
2056
+ "template": "{{bos_token}}{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}"
2057
+ },
2058
+ {
2059
+ "name": "tool_use",
2060
+ "template": "{%- macro json_to_python_type(json_spec) %}\n{%- set basic_type_map = {\n \"string\": \"str\",\n \"number\": \"float\",\n \"integer\": \"int\",\n \"boolean\": \"bool\"\n} %}\n\n{%- if basic_type_map[json_spec.type] is defined %}\n {{- basic_type_map[json_spec.type] }}\n{%- elif json_spec.type == \"array\" %}\n {{- \"list[\" + json_to_python_type(json_spec|items) + \"]\"}}\n{%- elif json_spec.type == \"object\" %}\n {%- if json_spec.additionalProperties is defined %}\n {{- \"dict[str, \" + json_to_python_type(json_spec.additionalProperties) + ']'}}\n {%- else %}\n {{- \"dict\" }}\n {%- endif %}\n{%- elif json_spec.type is iterable %}\n {{- \"Union[\" }}\n {%- for t in json_spec.type %}\n {{- json_to_python_type({\"type\": t}) }}\n {%- if not loop.last %}\n {{- \",\" }} \n {%- endif %}\n {%- endfor %}\n {{- \"]\" }}\n{%- else %}\n {{- \"Any\" }}\n{%- endif %}\n{%- endmacro %}\n\n\n{{- bos_token }}\n{{- '<|im_start|>system\n' }}\n{{- \"You are a function calling AI model. You are provided with function signatures within <tools></tools> XML tags. You may call one or more functions to assist with the user query. Don't make assumptions about what values to plug into functions. Here are the available tools: <tools> \" }}\n{%- for tool in tools %}\n {%- if tool.function is defined %}\n {%- set tool = tool.function %}\n {%- endif %}\n {{- '{\"type\": \"function\", \"function\": ' }}\n {{- '{\"name\": \"' + tool.name + '\", ' }}\n {{- '\"description\": \"' + tool.name + '(' }}\n {%- for param_name, param_fields in tool.parameters.properties|items %}\n {{- param_name + \": \" + json_to_python_type(param_fields) }}\n {%- if not loop.last %}\n {{- \", \" }}\n {%- endif %}\n {%- endfor %}\n {{- \")\" }}\n {%- if tool.return is defined %}\n {{- \" -> \" + json_to_python_type(tool.return) }}\n {%- endif %}\n {{- \" - \" + tool.description + \"\n\n\" }}\n {%- for param_name, param_fields in tool.parameters.properties|items %}\n {%- if loop.first %}\n {{- \" Args:\n\" }}\n {%- endif %}\n {{- \" \" + param_name + \"(\" + json_to_python_type(param_fields) + \"): \" + param_fields.description|trim }}\n {%- endfor %}\n {%- if tool.return is defined and tool.return.description is defined %}\n {{- \"\n Returns:\n \" + tool.return.description }}\n {%- endif %}\n {{- '\"' }}\n {{- ', \"parameters\": ' }}\n {%- if tool.parameters.properties | length == 0 %}\n {{- \"{}\" }}\n {%- else %}\n {{- tool.parameters|tojson }}\n {%- endif %}\n {{- \"}\" }}\n {%- if not loop.last %}\n {{- \"\n\" }}\n {%- endif %}\n{%- endfor %}\n{{- \" </tools>\" }}\n{{- 'Use the following pydantic model json schema for each tool call you will make: {\"properties\": {\"name\": {\"title\": \"Name\", \"type\": \"string\"}, \"arguments\": {\"title\": \"Arguments\", \"type\": \"object\"}}, \"required\": [\"name\", \"arguments\"], \"title\": \"FunctionCall\", \"type\": \"object\"}}\n' }}\n{{- \"For each function call return a json object with function name and arguments within <tool_call></tool_call> XML tags as follows:\n\" }}\n{{- \"<tool_call>\n\" }}\n{{- '{\"name\": <function-name>, \"arguments\": <args-dict>}\n' }}\n{{- '</tool_call><|im_end|>\n' }}\n{%- for message in messages %}\n {%- if message.role == \"user\" or message.role == \"system\" or (message.role == \"assistant\" and message.tool_calls is not defined) %}\n {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- for tool_call in message.tool_calls %}\n {{- '\n<tool_call>\n' }} {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '{' }}\n {{- '\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\"' }}\n {{- ', '}}\n {%- if tool_call.arguments is defined %}\n {{- '\"arguments\": ' }}\n {%- if tool_call.arguments is string %}\n {{- tool_call.arguments }}\n {%- else %}\n {{- tool_call.arguments|tojson }}\n {%- endif %}\n {%- endif %}\n {{- '}' }}\n {{- '\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.previtem and loop.previtem.role != \"tool\" %}\n {{- '<|im_start|>tool\n' }}\n {%- endif %}\n {{- '<tool_response>\n' }}\n {{- message.content }}\n {%- if not loop.last %}\n {{- '\n</tool_response>\n' }}\n {%- else %}\n {{- '\n</tool_response>' }}\n {%- endif %}\n {%- if not loop.last and loop.nextitem.role != \"tool\" %}\n {{- '<|im_end|>' }}\n {%- elif loop.last %}\n {{- '<|im_end|>' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\n' }}\n{%- endif %}\n"
2061
+ }
2062
+ ],
2063
+ "clean_up_tokenization_spaces": true,
2064
+ "eos_token": "<|im_end|>",
2065
+ "model_input_names": [
2066
+ "input_ids",
2067
+ "attention_mask"
2068
+ ],
2069
+ "model_max_length": 131072,
2070
+ "pad_token": "<|im_end|>",
2071
+ "tokenizer_class": "PreTrainedTokenizerFast"
2072
+ }
checkpoint-200/trainer_state.json ADDED
@@ -0,0 +1,393 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.6811409110259685,
5
+ "eval_steps": 500,
6
+ "global_step": 200,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.017028522775649212,
13
+ "grad_norm": 6.522716999053955,
14
+ "learning_rate": 0.0001988623435722412,
15
+ "loss": 2.7211,
16
+ "mean_token_accuracy": 0.5789041496813297,
17
+ "num_tokens": 4727.0,
18
+ "step": 5
19
+ },
20
+ {
21
+ "epoch": 0.034057045551298425,
22
+ "grad_norm": 1.0070050954818726,
23
+ "learning_rate": 0.00019772468714448238,
24
+ "loss": 0.9998,
25
+ "mean_token_accuracy": 0.8499793156981468,
26
+ "num_tokens": 9471.0,
27
+ "step": 10
28
+ },
29
+ {
30
+ "epoch": 0.05108556832694764,
31
+ "grad_norm": 0.7373425960540771,
32
+ "learning_rate": 0.00019658703071672356,
33
+ "loss": 0.8303,
34
+ "mean_token_accuracy": 0.8681916877627373,
35
+ "num_tokens": 14013.0,
36
+ "step": 15
37
+ },
38
+ {
39
+ "epoch": 0.06811409110259685,
40
+ "grad_norm": 0.8468236327171326,
41
+ "learning_rate": 0.00019544937428896475,
42
+ "loss": 0.8404,
43
+ "mean_token_accuracy": 0.8622620105743408,
44
+ "num_tokens": 18725.0,
45
+ "step": 20
46
+ },
47
+ {
48
+ "epoch": 0.08514261387824607,
49
+ "grad_norm": 0.8178804516792297,
50
+ "learning_rate": 0.00019431171786120593,
51
+ "loss": 0.9073,
52
+ "mean_token_accuracy": 0.8524447843432427,
53
+ "num_tokens": 23497.0,
54
+ "step": 25
55
+ },
56
+ {
57
+ "epoch": 0.10217113665389528,
58
+ "grad_norm": 0.890177309513092,
59
+ "learning_rate": 0.00019317406143344712,
60
+ "loss": 0.8029,
61
+ "mean_token_accuracy": 0.8642359614372254,
62
+ "num_tokens": 28192.0,
63
+ "step": 30
64
+ },
65
+ {
66
+ "epoch": 0.11919965942954448,
67
+ "grad_norm": 1.0545469522476196,
68
+ "learning_rate": 0.0001920364050056883,
69
+ "loss": 0.7458,
70
+ "mean_token_accuracy": 0.8732351213693619,
71
+ "num_tokens": 32805.0,
72
+ "step": 35
73
+ },
74
+ {
75
+ "epoch": 0.1362281822051937,
76
+ "grad_norm": 1.0384492874145508,
77
+ "learning_rate": 0.00019089874857792946,
78
+ "loss": 0.9235,
79
+ "mean_token_accuracy": 0.8408558666706085,
80
+ "num_tokens": 37714.0,
81
+ "step": 40
82
+ },
83
+ {
84
+ "epoch": 0.1532567049808429,
85
+ "grad_norm": 0.6860374808311462,
86
+ "learning_rate": 0.00018976109215017067,
87
+ "loss": 0.7623,
88
+ "mean_token_accuracy": 0.8656536340713501,
89
+ "num_tokens": 42429.0,
90
+ "step": 45
91
+ },
92
+ {
93
+ "epoch": 0.17028522775649213,
94
+ "grad_norm": 0.7284501791000366,
95
+ "learning_rate": 0.00018862343572241183,
96
+ "loss": 0.7588,
97
+ "mean_token_accuracy": 0.8688850715756417,
98
+ "num_tokens": 47099.0,
99
+ "step": 50
100
+ },
101
+ {
102
+ "epoch": 0.18731375053214133,
103
+ "grad_norm": 0.8899862170219421,
104
+ "learning_rate": 0.00018748577929465302,
105
+ "loss": 0.7065,
106
+ "mean_token_accuracy": 0.8717748820781708,
107
+ "num_tokens": 51795.0,
108
+ "step": 55
109
+ },
110
+ {
111
+ "epoch": 0.20434227330779056,
112
+ "grad_norm": 0.5350505709648132,
113
+ "learning_rate": 0.0001863481228668942,
114
+ "loss": 0.6696,
115
+ "mean_token_accuracy": 0.8851396456360817,
116
+ "num_tokens": 56369.0,
117
+ "step": 60
118
+ },
119
+ {
120
+ "epoch": 0.22137079608343976,
121
+ "grad_norm": 0.6087013483047485,
122
+ "learning_rate": 0.0001852104664391354,
123
+ "loss": 0.7204,
124
+ "mean_token_accuracy": 0.8682332798838616,
125
+ "num_tokens": 61018.0,
126
+ "step": 65
127
+ },
128
+ {
129
+ "epoch": 0.23839931885908897,
130
+ "grad_norm": 0.7879019379615784,
131
+ "learning_rate": 0.00018407281001137657,
132
+ "loss": 0.7692,
133
+ "mean_token_accuracy": 0.8653983056545258,
134
+ "num_tokens": 65741.0,
135
+ "step": 70
136
+ },
137
+ {
138
+ "epoch": 0.2554278416347382,
139
+ "grad_norm": 0.6546444296836853,
140
+ "learning_rate": 0.00018293515358361776,
141
+ "loss": 0.7119,
142
+ "mean_token_accuracy": 0.8726310178637504,
143
+ "num_tokens": 70425.0,
144
+ "step": 75
145
+ },
146
+ {
147
+ "epoch": 0.2724563644103874,
148
+ "grad_norm": 0.770902156829834,
149
+ "learning_rate": 0.00018179749715585894,
150
+ "loss": 0.7035,
151
+ "mean_token_accuracy": 0.8711811751127243,
152
+ "num_tokens": 75101.0,
153
+ "step": 80
154
+ },
155
+ {
156
+ "epoch": 0.2894848871860366,
157
+ "grad_norm": 0.8873187899589539,
158
+ "learning_rate": 0.00018065984072810013,
159
+ "loss": 0.7419,
160
+ "mean_token_accuracy": 0.8616803497076034,
161
+ "num_tokens": 79888.0,
162
+ "step": 85
163
+ },
164
+ {
165
+ "epoch": 0.3065134099616858,
166
+ "grad_norm": 0.7061370015144348,
167
+ "learning_rate": 0.0001795221843003413,
168
+ "loss": 0.66,
169
+ "mean_token_accuracy": 0.8744896531105042,
170
+ "num_tokens": 84562.0,
171
+ "step": 90
172
+ },
173
+ {
174
+ "epoch": 0.32354193273733506,
175
+ "grad_norm": 0.8232033252716064,
176
+ "learning_rate": 0.0001783845278725825,
177
+ "loss": 0.7403,
178
+ "mean_token_accuracy": 0.8659066379070282,
179
+ "num_tokens": 89238.0,
180
+ "step": 95
181
+ },
182
+ {
183
+ "epoch": 0.34057045551298426,
184
+ "grad_norm": 0.7313310503959656,
185
+ "learning_rate": 0.00017724687144482368,
186
+ "loss": 0.7157,
187
+ "mean_token_accuracy": 0.8661555901169777,
188
+ "num_tokens": 93987.0,
189
+ "step": 100
190
+ },
191
+ {
192
+ "epoch": 0.35759897828863346,
193
+ "grad_norm": 0.7119390964508057,
194
+ "learning_rate": 0.00017610921501706487,
195
+ "loss": 0.7016,
196
+ "mean_token_accuracy": 0.8678551658987999,
197
+ "num_tokens": 98722.0,
198
+ "step": 105
199
+ },
200
+ {
201
+ "epoch": 0.37462750106428266,
202
+ "grad_norm": 0.7126006484031677,
203
+ "learning_rate": 0.00017497155858930602,
204
+ "loss": 0.7009,
205
+ "mean_token_accuracy": 0.867291408777237,
206
+ "num_tokens": 103439.0,
207
+ "step": 110
208
+ },
209
+ {
210
+ "epoch": 0.39165602383993187,
211
+ "grad_norm": 0.6158230304718018,
212
+ "learning_rate": 0.00017383390216154724,
213
+ "loss": 0.7236,
214
+ "mean_token_accuracy": 0.8636128515005111,
215
+ "num_tokens": 108209.0,
216
+ "step": 115
217
+ },
218
+ {
219
+ "epoch": 0.4086845466155811,
220
+ "grad_norm": 0.6498322486877441,
221
+ "learning_rate": 0.0001726962457337884,
222
+ "loss": 0.6813,
223
+ "mean_token_accuracy": 0.8757071048021317,
224
+ "num_tokens": 112855.0,
225
+ "step": 120
226
+ },
227
+ {
228
+ "epoch": 0.4257130693912303,
229
+ "grad_norm": 0.6594287157058716,
230
+ "learning_rate": 0.0001715585893060296,
231
+ "loss": 0.7062,
232
+ "mean_token_accuracy": 0.8650311172008515,
233
+ "num_tokens": 117653.0,
234
+ "step": 125
235
+ },
236
+ {
237
+ "epoch": 0.4427415921668795,
238
+ "grad_norm": 0.7375237941741943,
239
+ "learning_rate": 0.00017042093287827076,
240
+ "loss": 0.6477,
241
+ "mean_token_accuracy": 0.8733970731496811,
242
+ "num_tokens": 122397.0,
243
+ "step": 130
244
+ },
245
+ {
246
+ "epoch": 0.45977011494252873,
247
+ "grad_norm": 0.5958442687988281,
248
+ "learning_rate": 0.00016928327645051198,
249
+ "loss": 0.691,
250
+ "mean_token_accuracy": 0.8681387722492218,
251
+ "num_tokens": 127136.0,
252
+ "step": 135
253
+ },
254
+ {
255
+ "epoch": 0.47679863771817793,
256
+ "grad_norm": 0.7407785654067993,
257
+ "learning_rate": 0.00016814562002275313,
258
+ "loss": 0.6477,
259
+ "mean_token_accuracy": 0.8752307429909706,
260
+ "num_tokens": 131833.0,
261
+ "step": 140
262
+ },
263
+ {
264
+ "epoch": 0.49382716049382713,
265
+ "grad_norm": 0.8190199732780457,
266
+ "learning_rate": 0.00016700796359499432,
267
+ "loss": 0.6608,
268
+ "mean_token_accuracy": 0.8762851104140281,
269
+ "num_tokens": 136441.0,
270
+ "step": 145
271
+ },
272
+ {
273
+ "epoch": 0.5108556832694764,
274
+ "grad_norm": 0.7571837306022644,
275
+ "learning_rate": 0.0001658703071672355,
276
+ "loss": 0.673,
277
+ "mean_token_accuracy": 0.8691665843129158,
278
+ "num_tokens": 141186.0,
279
+ "step": 150
280
+ },
281
+ {
282
+ "epoch": 0.5278842060451255,
283
+ "grad_norm": 0.6653426885604858,
284
+ "learning_rate": 0.0001647326507394767,
285
+ "loss": 0.7126,
286
+ "mean_token_accuracy": 0.8647830635309219,
287
+ "num_tokens": 145971.0,
288
+ "step": 155
289
+ },
290
+ {
291
+ "epoch": 0.5449127288207748,
292
+ "grad_norm": 0.7333567142486572,
293
+ "learning_rate": 0.00016359499431171787,
294
+ "loss": 0.6287,
295
+ "mean_token_accuracy": 0.878324082493782,
296
+ "num_tokens": 150669.0,
297
+ "step": 160
298
+ },
299
+ {
300
+ "epoch": 0.561941251596424,
301
+ "grad_norm": 0.8214460015296936,
302
+ "learning_rate": 0.00016245733788395906,
303
+ "loss": 0.6608,
304
+ "mean_token_accuracy": 0.8729922890663147,
305
+ "num_tokens": 155374.0,
306
+ "step": 165
307
+ },
308
+ {
309
+ "epoch": 0.5789697743720732,
310
+ "grad_norm": 0.6251844167709351,
311
+ "learning_rate": 0.00016131968145620024,
312
+ "loss": 0.6556,
313
+ "mean_token_accuracy": 0.8770609870553017,
314
+ "num_tokens": 160068.0,
315
+ "step": 170
316
+ },
317
+ {
318
+ "epoch": 0.5959982971477225,
319
+ "grad_norm": 0.804166853427887,
320
+ "learning_rate": 0.00016018202502844143,
321
+ "loss": 0.6366,
322
+ "mean_token_accuracy": 0.8760894432663917,
323
+ "num_tokens": 164696.0,
324
+ "step": 175
325
+ },
326
+ {
327
+ "epoch": 0.6130268199233716,
328
+ "grad_norm": 0.7013877034187317,
329
+ "learning_rate": 0.0001590443686006826,
330
+ "loss": 0.6328,
331
+ "mean_token_accuracy": 0.8779815405607223,
332
+ "num_tokens": 169356.0,
333
+ "step": 180
334
+ },
335
+ {
336
+ "epoch": 0.6300553426990209,
337
+ "grad_norm": 1.0623070001602173,
338
+ "learning_rate": 0.0001579067121729238,
339
+ "loss": 0.6734,
340
+ "mean_token_accuracy": 0.8710577815771103,
341
+ "num_tokens": 174041.0,
342
+ "step": 185
343
+ },
344
+ {
345
+ "epoch": 0.6470838654746701,
346
+ "grad_norm": 0.7858535647392273,
347
+ "learning_rate": 0.00015676905574516496,
348
+ "loss": 0.6775,
349
+ "mean_token_accuracy": 0.8692880481481552,
350
+ "num_tokens": 178858.0,
351
+ "step": 190
352
+ },
353
+ {
354
+ "epoch": 0.6641123882503193,
355
+ "grad_norm": 0.8943309187889099,
356
+ "learning_rate": 0.00015563139931740617,
357
+ "loss": 0.6874,
358
+ "mean_token_accuracy": 0.868885512650013,
359
+ "num_tokens": 183669.0,
360
+ "step": 195
361
+ },
362
+ {
363
+ "epoch": 0.6811409110259685,
364
+ "grad_norm": 0.5898745656013489,
365
+ "learning_rate": 0.00015449374288964733,
366
+ "loss": 0.6907,
367
+ "mean_token_accuracy": 0.8661940798163414,
368
+ "num_tokens": 188473.0,
369
+ "step": 200
370
+ }
371
+ ],
372
+ "logging_steps": 5,
373
+ "max_steps": 879,
374
+ "num_input_tokens_seen": 0,
375
+ "num_train_epochs": 3,
376
+ "save_steps": 200,
377
+ "stateful_callbacks": {
378
+ "TrainerControl": {
379
+ "args": {
380
+ "should_epoch_stop": false,
381
+ "should_evaluate": false,
382
+ "should_log": false,
383
+ "should_save": true,
384
+ "should_training_stop": false
385
+ },
386
+ "attributes": {}
387
+ }
388
+ },
389
+ "total_flos": 8534284789702656.0,
390
+ "train_batch_size": 1,
391
+ "trial_name": null,
392
+ "trial_params": null
393
+ }
checkpoint-200/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc4e07dc6df6129e6d2045027becfa7300f4a8ae9e98a02f1c9d1066e93703ce
3
+ size 5624
checkpoint-400/README.md ADDED
@@ -0,0 +1,209 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: NousResearch/Hermes-3-Llama-3.1-8B
3
+ library_name: peft
4
+ pipeline_tag: text-generation
5
+ tags:
6
+ - base_model:adapter:NousResearch/Hermes-3-Llama-3.1-8B
7
+ - lora
8
+ - sft
9
+ - transformers
10
+ - trl
11
+ ---
12
+
13
+ # Model Card for Model ID
14
+
15
+ <!-- Provide a quick summary of what the model is/does. -->
16
+
17
+
18
+
19
+ ## Model Details
20
+
21
+ ### Model Description
22
+
23
+ <!-- Provide a longer summary of what this model is. -->
24
+
25
+
26
+
27
+ - **Developed by:** [More Information Needed]
28
+ - **Funded by [optional]:** [More Information Needed]
29
+ - **Shared by [optional]:** [More Information Needed]
30
+ - **Model type:** [More Information Needed]
31
+ - **Language(s) (NLP):** [More Information Needed]
32
+ - **License:** [More Information Needed]
33
+ - **Finetuned from model [optional]:** [More Information Needed]
34
+
35
+ ### Model Sources [optional]
36
+
37
+ <!-- Provide the basic links for the model. -->
38
+
39
+ - **Repository:** [More Information Needed]
40
+ - **Paper [optional]:** [More Information Needed]
41
+ - **Demo [optional]:** [More Information Needed]
42
+
43
+ ## Uses
44
+
45
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
46
+
47
+ ### Direct Use
48
+
49
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
50
+
51
+ [More Information Needed]
52
+
53
+ ### Downstream Use [optional]
54
+
55
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
56
+
57
+ [More Information Needed]
58
+
59
+ ### Out-of-Scope Use
60
+
61
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
62
+
63
+ [More Information Needed]
64
+
65
+ ## Bias, Risks, and Limitations
66
+
67
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
68
+
69
+ [More Information Needed]
70
+
71
+ ### Recommendations
72
+
73
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
74
+
75
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
76
+
77
+ ## How to Get Started with the Model
78
+
79
+ Use the code below to get started with the model.
80
+
81
+ [More Information Needed]
82
+
83
+ ## Training Details
84
+
85
+ ### Training Data
86
+
87
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
88
+
89
+ [More Information Needed]
90
+
91
+ ### Training Procedure
92
+
93
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
94
+
95
+ #### Preprocessing [optional]
96
+
97
+ [More Information Needed]
98
+
99
+
100
+ #### Training Hyperparameters
101
+
102
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
103
+
104
+ #### Speeds, Sizes, Times [optional]
105
+
106
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
107
+
108
+ [More Information Needed]
109
+
110
+ ## Evaluation
111
+
112
+ <!-- This section describes the evaluation protocols and provides the results. -->
113
+
114
+ ### Testing Data, Factors & Metrics
115
+
116
+ #### Testing Data
117
+
118
+ <!-- This should link to a Dataset Card if possible. -->
119
+
120
+ [More Information Needed]
121
+
122
+ #### Factors
123
+
124
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
125
+
126
+ [More Information Needed]
127
+
128
+ #### Metrics
129
+
130
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
131
+
132
+ [More Information Needed]
133
+
134
+ ### Results
135
+
136
+ [More Information Needed]
137
+
138
+ #### Summary
139
+
140
+
141
+
142
+ ## Model Examination [optional]
143
+
144
+ <!-- Relevant interpretability work for the model goes here -->
145
+
146
+ [More Information Needed]
147
+
148
+ ## Environmental Impact
149
+
150
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
151
+
152
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
153
+
154
+ - **Hardware Type:** [More Information Needed]
155
+ - **Hours used:** [More Information Needed]
156
+ - **Cloud Provider:** [More Information Needed]
157
+ - **Compute Region:** [More Information Needed]
158
+ - **Carbon Emitted:** [More Information Needed]
159
+
160
+ ## Technical Specifications [optional]
161
+
162
+ ### Model Architecture and Objective
163
+
164
+ [More Information Needed]
165
+
166
+ ### Compute Infrastructure
167
+
168
+ [More Information Needed]
169
+
170
+ #### Hardware
171
+
172
+ [More Information Needed]
173
+
174
+ #### Software
175
+
176
+ [More Information Needed]
177
+
178
+ ## Citation [optional]
179
+
180
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
181
+
182
+ **BibTeX:**
183
+
184
+ [More Information Needed]
185
+
186
+ **APA:**
187
+
188
+ [More Information Needed]
189
+
190
+ ## Glossary [optional]
191
+
192
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
193
+
194
+ [More Information Needed]
195
+
196
+ ## More Information [optional]
197
+
198
+ [More Information Needed]
199
+
200
+ ## Model Card Authors [optional]
201
+
202
+ [More Information Needed]
203
+
204
+ ## Model Card Contact
205
+
206
+ [More Information Needed]
207
+ ### Framework versions
208
+
209
+ - PEFT 0.20.0
checkpoint-400/adapter_config.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alora_invocation_tokens": null,
3
+ "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": null,
6
+ "base_model_name_or_path": "NousResearch/Hermes-3-Llama-3.1-8B",
7
+ "bias": "none",
8
+ "corda_config": null,
9
+ "ensure_weight_tying": false,
10
+ "eva_config": null,
11
+ "exclude_modules": null,
12
+ "fan_in_fan_out": false,
13
+ "inference_mode": true,
14
+ "init_lora_weights": true,
15
+ "layer_replication": null,
16
+ "layers_pattern": null,
17
+ "layers_to_transform": null,
18
+ "loftq_config": {},
19
+ "lora_alpha": 32,
20
+ "lora_bias": false,
21
+ "lora_dropout": 0.05,
22
+ "lora_ga_config": null,
23
+ "megatron_config": null,
24
+ "megatron_core": "megatron.core",
25
+ "modules_to_save": null,
26
+ "monteclora_config": null,
27
+ "peft_type": "LORA",
28
+ "peft_version": "0.20.0",
29
+ "qalora_group_size": 16,
30
+ "r": 16,
31
+ "rank_pattern": {},
32
+ "revision": null,
33
+ "target_modules": [
34
+ "v_proj",
35
+ "q_proj",
36
+ "k_proj",
37
+ "down_proj",
38
+ "up_proj",
39
+ "gate_proj",
40
+ "o_proj"
41
+ ],
42
+ "target_parameters": null,
43
+ "task_type": "CAUSAL_LM",
44
+ "trainable_token_indices": null,
45
+ "use_bdlora": null,
46
+ "use_dora": false,
47
+ "use_qalora": false,
48
+ "use_rslora": false,
49
+ "velora_config": null
50
+ }
checkpoint-400/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b8ac362c6bd18e2a2c20a4f44f1882f568e0f879c22cab4e217443450541c89
3
+ size 167832240
checkpoint-400/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78446832e6777e949471c8a7423ef18a9785aa589bd11dc1011a7552cc2050c7
3
+ size 85728276
checkpoint-400/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80d5f2e1daf718d7f4b153fb015cfb1eab12c9439e2a47cb1a9d7e57dbe69344
3
+ size 14244
checkpoint-400/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fbaa767a1867f6f8022ea209ef1a03a369e44768800ec83f2966bcd9939650bb
3
+ size 1064
checkpoint-400/special_tokens_map.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|im_end|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|im_end|>"
17
+ }
checkpoint-400/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14b5e679cb69af62e14c3b98d346177bd4137d882a44f87dec9efec982b01a05
3
+ size 17209403
checkpoint-400/tokenizer_config.json ADDED
@@ -0,0 +1,2072 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<tool_call>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": false
26
+ },
27
+ "128003": {
28
+ "content": "<tool_response>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": false
34
+ },
35
+ "128004": {
36
+ "content": "<|finetune_right_pad_id|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_2|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128006": {
52
+ "content": "<|start_header_id|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "128007": {
60
+ "content": "<|end_header_id|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "128008": {
68
+ "content": "<|eom_id|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "128009": {
76
+ "content": "<|eot_id|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "128010": {
84
+ "content": "<|python_tag|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<tools>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": false
98
+ },
99
+ "128012": {
100
+ "content": "</tools>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": false
106
+ },
107
+ "128013": {
108
+ "content": "</tool_call>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": false
114
+ },
115
+ "128014": {
116
+ "content": "</tool_response>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": false
122
+ },
123
+ "128015": {
124
+ "content": "<schema>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": false
130
+ },
131
+ "128016": {
132
+ "content": "</schema>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": false
138
+ },
139
+ "128017": {
140
+ "content": "<scratch_pad>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": false
146
+ },
147
+ "128018": {
148
+ "content": "</scratch_pad>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": false
154
+ },
155
+ "128019": {
156
+ "content": "<SCRATCHPAD>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": false
162
+ },
163
+ "128020": {
164
+ "content": "</SCRATCHPAD>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": false
170
+ },
171
+ "128021": {
172
+ "content": "<REASONING>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": false
178
+ },
179
+ "128022": {
180
+ "content": "</REASONING>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": false
186
+ },
187
+ "128023": {
188
+ "content": "<INNER_MONOLOGUE>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": false
194
+ },
195
+ "128024": {
196
+ "content": "</INNER_MONOLOGUE>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": false
202
+ },
203
+ "128025": {
204
+ "content": "<PLAN>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": false
210
+ },
211
+ "128026": {
212
+ "content": "</PLAN>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": false
218
+ },
219
+ "128027": {
220
+ "content": "<EXECUTION>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": false
226
+ },
227
+ "128028": {
228
+ "content": "</EXECUTION>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": false
234
+ },
235
+ "128029": {
236
+ "content": "<REFLECTION>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": false
242
+ },
243
+ "128030": {
244
+ "content": "</REFLECTION>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": false
250
+ },
251
+ "128031": {
252
+ "content": "<THINKING>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": false
258
+ },
259
+ "128032": {
260
+ "content": "</THINKING>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": false
266
+ },
267
+ "128033": {
268
+ "content": "<SOLUTION>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": false
274
+ },
275
+ "128034": {
276
+ "content": "</SOLUTION>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": false
282
+ },
283
+ "128035": {
284
+ "content": "<EXPLANATION>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": false
290
+ },
291
+ "128036": {
292
+ "content": "</EXPLANATION>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": false
298
+ },
299
+ "128037": {
300
+ "content": "<UNIT_TEST>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": false
306
+ },
307
+ "128038": {
308
+ "content": "</UNIT_TEST>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": false
314
+ },
315
+ "128039": {
316
+ "content": "<|im_start|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": false
322
+ },
323
+ "128040": {
324
+ "content": "<|im_end|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_33|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_34|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_35|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_36|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_37|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_38|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_39|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_40|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_41|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_42|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_43|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_44|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_45|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_46|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_47|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_48|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_49|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_50|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_51|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_52|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_53|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_54|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_55|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_56|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_57|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_58|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_59|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_60|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_61|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_62|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_63|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_64|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_65|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_66|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_67|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_68|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_69|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_70|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_71|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_72|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_73|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_74|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_75|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_76|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_77|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_78|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_79|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_80|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_81|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_82|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_83|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_84|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_85|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_86|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_87|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_88|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_89|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_90|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_91|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_92|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_93|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_94|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_95|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_96|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_97|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_98|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_99|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_100|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_101|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_102|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_103|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_104|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_105|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_106|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_107|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_108|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_109|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_110|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_111|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_112|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_113|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_114|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_115|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_116|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_117|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_118|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_119|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_120|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_121|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_122|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_123|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_124|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_125|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_126|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_127|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_128|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_129|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_130|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_131|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_132|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_133|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_134|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_135|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_136|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_137|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_138|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_139|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_140|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_141|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_142|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_143|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_144|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_145|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_146|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_147|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_148|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_149|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_150|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_151|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_152|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_153|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_154|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_155|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_156|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_157|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_158|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_159|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_160|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_161|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_162|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_163|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_164|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_165|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_166|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_167|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_168|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_169|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_170|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_171|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_172|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_173|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_174|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_175|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_176|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_177|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_178|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_179|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_180|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_181|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_182|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_183|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_184|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_185|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_186|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_187|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_188|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_189|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_190|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_191|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_192|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_193|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_194|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_195|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_196|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_197|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_198|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_199|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_200|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_201|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_202|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_203|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_204|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_205|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_206|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_207|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_208|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_209|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_210|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_211|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_212|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_213|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_214|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_215|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_216|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_217|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_218|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_219|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_220|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_221|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_222|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_223|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_224|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_225|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_226|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_227|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_228|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_229|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_230|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_231|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_232|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_233|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_234|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_235|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_236|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_237|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_238|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_239|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_240|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_241|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_242|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_243|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_244|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_245|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_246|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_247|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ }
2051
+ },
2052
+ "bos_token": "<|begin_of_text|>",
2053
+ "chat_template": [
2054
+ {
2055
+ "name": "default",
2056
+ "template": "{{bos_token}}{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}"
2057
+ },
2058
+ {
2059
+ "name": "tool_use",
2060
+ "template": "{%- macro json_to_python_type(json_spec) %}\n{%- set basic_type_map = {\n \"string\": \"str\",\n \"number\": \"float\",\n \"integer\": \"int\",\n \"boolean\": \"bool\"\n} %}\n\n{%- if basic_type_map[json_spec.type] is defined %}\n {{- basic_type_map[json_spec.type] }}\n{%- elif json_spec.type == \"array\" %}\n {{- \"list[\" + json_to_python_type(json_spec|items) + \"]\"}}\n{%- elif json_spec.type == \"object\" %}\n {%- if json_spec.additionalProperties is defined %}\n {{- \"dict[str, \" + json_to_python_type(json_spec.additionalProperties) + ']'}}\n {%- else %}\n {{- \"dict\" }}\n {%- endif %}\n{%- elif json_spec.type is iterable %}\n {{- \"Union[\" }}\n {%- for t in json_spec.type %}\n {{- json_to_python_type({\"type\": t}) }}\n {%- if not loop.last %}\n {{- \",\" }} \n {%- endif %}\n {%- endfor %}\n {{- \"]\" }}\n{%- else %}\n {{- \"Any\" }}\n{%- endif %}\n{%- endmacro %}\n\n\n{{- bos_token }}\n{{- '<|im_start|>system\n' }}\n{{- \"You are a function calling AI model. You are provided with function signatures within <tools></tools> XML tags. You may call one or more functions to assist with the user query. Don't make assumptions about what values to plug into functions. Here are the available tools: <tools> \" }}\n{%- for tool in tools %}\n {%- if tool.function is defined %}\n {%- set tool = tool.function %}\n {%- endif %}\n {{- '{\"type\": \"function\", \"function\": ' }}\n {{- '{\"name\": \"' + tool.name + '\", ' }}\n {{- '\"description\": \"' + tool.name + '(' }}\n {%- for param_name, param_fields in tool.parameters.properties|items %}\n {{- param_name + \": \" + json_to_python_type(param_fields) }}\n {%- if not loop.last %}\n {{- \", \" }}\n {%- endif %}\n {%- endfor %}\n {{- \")\" }}\n {%- if tool.return is defined %}\n {{- \" -> \" + json_to_python_type(tool.return) }}\n {%- endif %}\n {{- \" - \" + tool.description + \"\n\n\" }}\n {%- for param_name, param_fields in tool.parameters.properties|items %}\n {%- if loop.first %}\n {{- \" Args:\n\" }}\n {%- endif %}\n {{- \" \" + param_name + \"(\" + json_to_python_type(param_fields) + \"): \" + param_fields.description|trim }}\n {%- endfor %}\n {%- if tool.return is defined and tool.return.description is defined %}\n {{- \"\n Returns:\n \" + tool.return.description }}\n {%- endif %}\n {{- '\"' }}\n {{- ', \"parameters\": ' }}\n {%- if tool.parameters.properties | length == 0 %}\n {{- \"{}\" }}\n {%- else %}\n {{- tool.parameters|tojson }}\n {%- endif %}\n {{- \"}\" }}\n {%- if not loop.last %}\n {{- \"\n\" }}\n {%- endif %}\n{%- endfor %}\n{{- \" </tools>\" }}\n{{- 'Use the following pydantic model json schema for each tool call you will make: {\"properties\": {\"name\": {\"title\": \"Name\", \"type\": \"string\"}, \"arguments\": {\"title\": \"Arguments\", \"type\": \"object\"}}, \"required\": [\"name\", \"arguments\"], \"title\": \"FunctionCall\", \"type\": \"object\"}}\n' }}\n{{- \"For each function call return a json object with function name and arguments within <tool_call></tool_call> XML tags as follows:\n\" }}\n{{- \"<tool_call>\n\" }}\n{{- '{\"name\": <function-name>, \"arguments\": <args-dict>}\n' }}\n{{- '</tool_call><|im_end|>\n' }}\n{%- for message in messages %}\n {%- if message.role == \"user\" or message.role == \"system\" or (message.role == \"assistant\" and message.tool_calls is not defined) %}\n {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- for tool_call in message.tool_calls %}\n {{- '\n<tool_call>\n' }} {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '{' }}\n {{- '\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\"' }}\n {{- ', '}}\n {%- if tool_call.arguments is defined %}\n {{- '\"arguments\": ' }}\n {%- if tool_call.arguments is string %}\n {{- tool_call.arguments }}\n {%- else %}\n {{- tool_call.arguments|tojson }}\n {%- endif %}\n {%- endif %}\n {{- '}' }}\n {{- '\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.previtem and loop.previtem.role != \"tool\" %}\n {{- '<|im_start|>tool\n' }}\n {%- endif %}\n {{- '<tool_response>\n' }}\n {{- message.content }}\n {%- if not loop.last %}\n {{- '\n</tool_response>\n' }}\n {%- else %}\n {{- '\n</tool_response>' }}\n {%- endif %}\n {%- if not loop.last and loop.nextitem.role != \"tool\" %}\n {{- '<|im_end|>' }}\n {%- elif loop.last %}\n {{- '<|im_end|>' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\n' }}\n{%- endif %}\n"
2061
+ }
2062
+ ],
2063
+ "clean_up_tokenization_spaces": true,
2064
+ "eos_token": "<|im_end|>",
2065
+ "model_input_names": [
2066
+ "input_ids",
2067
+ "attention_mask"
2068
+ ],
2069
+ "model_max_length": 131072,
2070
+ "pad_token": "<|im_end|>",
2071
+ "tokenizer_class": "PreTrainedTokenizerFast"
2072
+ }
checkpoint-400/trainer_state.json ADDED
@@ -0,0 +1,753 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.362281822051937,
5
+ "eval_steps": 500,
6
+ "global_step": 400,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.017028522775649212,
13
+ "grad_norm": 6.522716999053955,
14
+ "learning_rate": 0.0001988623435722412,
15
+ "loss": 2.7211,
16
+ "mean_token_accuracy": 0.5789041496813297,
17
+ "num_tokens": 4727.0,
18
+ "step": 5
19
+ },
20
+ {
21
+ "epoch": 0.034057045551298425,
22
+ "grad_norm": 1.0070050954818726,
23
+ "learning_rate": 0.00019772468714448238,
24
+ "loss": 0.9998,
25
+ "mean_token_accuracy": 0.8499793156981468,
26
+ "num_tokens": 9471.0,
27
+ "step": 10
28
+ },
29
+ {
30
+ "epoch": 0.05108556832694764,
31
+ "grad_norm": 0.7373425960540771,
32
+ "learning_rate": 0.00019658703071672356,
33
+ "loss": 0.8303,
34
+ "mean_token_accuracy": 0.8681916877627373,
35
+ "num_tokens": 14013.0,
36
+ "step": 15
37
+ },
38
+ {
39
+ "epoch": 0.06811409110259685,
40
+ "grad_norm": 0.8468236327171326,
41
+ "learning_rate": 0.00019544937428896475,
42
+ "loss": 0.8404,
43
+ "mean_token_accuracy": 0.8622620105743408,
44
+ "num_tokens": 18725.0,
45
+ "step": 20
46
+ },
47
+ {
48
+ "epoch": 0.08514261387824607,
49
+ "grad_norm": 0.8178804516792297,
50
+ "learning_rate": 0.00019431171786120593,
51
+ "loss": 0.9073,
52
+ "mean_token_accuracy": 0.8524447843432427,
53
+ "num_tokens": 23497.0,
54
+ "step": 25
55
+ },
56
+ {
57
+ "epoch": 0.10217113665389528,
58
+ "grad_norm": 0.890177309513092,
59
+ "learning_rate": 0.00019317406143344712,
60
+ "loss": 0.8029,
61
+ "mean_token_accuracy": 0.8642359614372254,
62
+ "num_tokens": 28192.0,
63
+ "step": 30
64
+ },
65
+ {
66
+ "epoch": 0.11919965942954448,
67
+ "grad_norm": 1.0545469522476196,
68
+ "learning_rate": 0.0001920364050056883,
69
+ "loss": 0.7458,
70
+ "mean_token_accuracy": 0.8732351213693619,
71
+ "num_tokens": 32805.0,
72
+ "step": 35
73
+ },
74
+ {
75
+ "epoch": 0.1362281822051937,
76
+ "grad_norm": 1.0384492874145508,
77
+ "learning_rate": 0.00019089874857792946,
78
+ "loss": 0.9235,
79
+ "mean_token_accuracy": 0.8408558666706085,
80
+ "num_tokens": 37714.0,
81
+ "step": 40
82
+ },
83
+ {
84
+ "epoch": 0.1532567049808429,
85
+ "grad_norm": 0.6860374808311462,
86
+ "learning_rate": 0.00018976109215017067,
87
+ "loss": 0.7623,
88
+ "mean_token_accuracy": 0.8656536340713501,
89
+ "num_tokens": 42429.0,
90
+ "step": 45
91
+ },
92
+ {
93
+ "epoch": 0.17028522775649213,
94
+ "grad_norm": 0.7284501791000366,
95
+ "learning_rate": 0.00018862343572241183,
96
+ "loss": 0.7588,
97
+ "mean_token_accuracy": 0.8688850715756417,
98
+ "num_tokens": 47099.0,
99
+ "step": 50
100
+ },
101
+ {
102
+ "epoch": 0.18731375053214133,
103
+ "grad_norm": 0.8899862170219421,
104
+ "learning_rate": 0.00018748577929465302,
105
+ "loss": 0.7065,
106
+ "mean_token_accuracy": 0.8717748820781708,
107
+ "num_tokens": 51795.0,
108
+ "step": 55
109
+ },
110
+ {
111
+ "epoch": 0.20434227330779056,
112
+ "grad_norm": 0.5350505709648132,
113
+ "learning_rate": 0.0001863481228668942,
114
+ "loss": 0.6696,
115
+ "mean_token_accuracy": 0.8851396456360817,
116
+ "num_tokens": 56369.0,
117
+ "step": 60
118
+ },
119
+ {
120
+ "epoch": 0.22137079608343976,
121
+ "grad_norm": 0.6087013483047485,
122
+ "learning_rate": 0.0001852104664391354,
123
+ "loss": 0.7204,
124
+ "mean_token_accuracy": 0.8682332798838616,
125
+ "num_tokens": 61018.0,
126
+ "step": 65
127
+ },
128
+ {
129
+ "epoch": 0.23839931885908897,
130
+ "grad_norm": 0.7879019379615784,
131
+ "learning_rate": 0.00018407281001137657,
132
+ "loss": 0.7692,
133
+ "mean_token_accuracy": 0.8653983056545258,
134
+ "num_tokens": 65741.0,
135
+ "step": 70
136
+ },
137
+ {
138
+ "epoch": 0.2554278416347382,
139
+ "grad_norm": 0.6546444296836853,
140
+ "learning_rate": 0.00018293515358361776,
141
+ "loss": 0.7119,
142
+ "mean_token_accuracy": 0.8726310178637504,
143
+ "num_tokens": 70425.0,
144
+ "step": 75
145
+ },
146
+ {
147
+ "epoch": 0.2724563644103874,
148
+ "grad_norm": 0.770902156829834,
149
+ "learning_rate": 0.00018179749715585894,
150
+ "loss": 0.7035,
151
+ "mean_token_accuracy": 0.8711811751127243,
152
+ "num_tokens": 75101.0,
153
+ "step": 80
154
+ },
155
+ {
156
+ "epoch": 0.2894848871860366,
157
+ "grad_norm": 0.8873187899589539,
158
+ "learning_rate": 0.00018065984072810013,
159
+ "loss": 0.7419,
160
+ "mean_token_accuracy": 0.8616803497076034,
161
+ "num_tokens": 79888.0,
162
+ "step": 85
163
+ },
164
+ {
165
+ "epoch": 0.3065134099616858,
166
+ "grad_norm": 0.7061370015144348,
167
+ "learning_rate": 0.0001795221843003413,
168
+ "loss": 0.66,
169
+ "mean_token_accuracy": 0.8744896531105042,
170
+ "num_tokens": 84562.0,
171
+ "step": 90
172
+ },
173
+ {
174
+ "epoch": 0.32354193273733506,
175
+ "grad_norm": 0.8232033252716064,
176
+ "learning_rate": 0.0001783845278725825,
177
+ "loss": 0.7403,
178
+ "mean_token_accuracy": 0.8659066379070282,
179
+ "num_tokens": 89238.0,
180
+ "step": 95
181
+ },
182
+ {
183
+ "epoch": 0.34057045551298426,
184
+ "grad_norm": 0.7313310503959656,
185
+ "learning_rate": 0.00017724687144482368,
186
+ "loss": 0.7157,
187
+ "mean_token_accuracy": 0.8661555901169777,
188
+ "num_tokens": 93987.0,
189
+ "step": 100
190
+ },
191
+ {
192
+ "epoch": 0.35759897828863346,
193
+ "grad_norm": 0.7119390964508057,
194
+ "learning_rate": 0.00017610921501706487,
195
+ "loss": 0.7016,
196
+ "mean_token_accuracy": 0.8678551658987999,
197
+ "num_tokens": 98722.0,
198
+ "step": 105
199
+ },
200
+ {
201
+ "epoch": 0.37462750106428266,
202
+ "grad_norm": 0.7126006484031677,
203
+ "learning_rate": 0.00017497155858930602,
204
+ "loss": 0.7009,
205
+ "mean_token_accuracy": 0.867291408777237,
206
+ "num_tokens": 103439.0,
207
+ "step": 110
208
+ },
209
+ {
210
+ "epoch": 0.39165602383993187,
211
+ "grad_norm": 0.6158230304718018,
212
+ "learning_rate": 0.00017383390216154724,
213
+ "loss": 0.7236,
214
+ "mean_token_accuracy": 0.8636128515005111,
215
+ "num_tokens": 108209.0,
216
+ "step": 115
217
+ },
218
+ {
219
+ "epoch": 0.4086845466155811,
220
+ "grad_norm": 0.6498322486877441,
221
+ "learning_rate": 0.0001726962457337884,
222
+ "loss": 0.6813,
223
+ "mean_token_accuracy": 0.8757071048021317,
224
+ "num_tokens": 112855.0,
225
+ "step": 120
226
+ },
227
+ {
228
+ "epoch": 0.4257130693912303,
229
+ "grad_norm": 0.6594287157058716,
230
+ "learning_rate": 0.0001715585893060296,
231
+ "loss": 0.7062,
232
+ "mean_token_accuracy": 0.8650311172008515,
233
+ "num_tokens": 117653.0,
234
+ "step": 125
235
+ },
236
+ {
237
+ "epoch": 0.4427415921668795,
238
+ "grad_norm": 0.7375237941741943,
239
+ "learning_rate": 0.00017042093287827076,
240
+ "loss": 0.6477,
241
+ "mean_token_accuracy": 0.8733970731496811,
242
+ "num_tokens": 122397.0,
243
+ "step": 130
244
+ },
245
+ {
246
+ "epoch": 0.45977011494252873,
247
+ "grad_norm": 0.5958442687988281,
248
+ "learning_rate": 0.00016928327645051198,
249
+ "loss": 0.691,
250
+ "mean_token_accuracy": 0.8681387722492218,
251
+ "num_tokens": 127136.0,
252
+ "step": 135
253
+ },
254
+ {
255
+ "epoch": 0.47679863771817793,
256
+ "grad_norm": 0.7407785654067993,
257
+ "learning_rate": 0.00016814562002275313,
258
+ "loss": 0.6477,
259
+ "mean_token_accuracy": 0.8752307429909706,
260
+ "num_tokens": 131833.0,
261
+ "step": 140
262
+ },
263
+ {
264
+ "epoch": 0.49382716049382713,
265
+ "grad_norm": 0.8190199732780457,
266
+ "learning_rate": 0.00016700796359499432,
267
+ "loss": 0.6608,
268
+ "mean_token_accuracy": 0.8762851104140281,
269
+ "num_tokens": 136441.0,
270
+ "step": 145
271
+ },
272
+ {
273
+ "epoch": 0.5108556832694764,
274
+ "grad_norm": 0.7571837306022644,
275
+ "learning_rate": 0.0001658703071672355,
276
+ "loss": 0.673,
277
+ "mean_token_accuracy": 0.8691665843129158,
278
+ "num_tokens": 141186.0,
279
+ "step": 150
280
+ },
281
+ {
282
+ "epoch": 0.5278842060451255,
283
+ "grad_norm": 0.6653426885604858,
284
+ "learning_rate": 0.0001647326507394767,
285
+ "loss": 0.7126,
286
+ "mean_token_accuracy": 0.8647830635309219,
287
+ "num_tokens": 145971.0,
288
+ "step": 155
289
+ },
290
+ {
291
+ "epoch": 0.5449127288207748,
292
+ "grad_norm": 0.7333567142486572,
293
+ "learning_rate": 0.00016359499431171787,
294
+ "loss": 0.6287,
295
+ "mean_token_accuracy": 0.878324082493782,
296
+ "num_tokens": 150669.0,
297
+ "step": 160
298
+ },
299
+ {
300
+ "epoch": 0.561941251596424,
301
+ "grad_norm": 0.8214460015296936,
302
+ "learning_rate": 0.00016245733788395906,
303
+ "loss": 0.6608,
304
+ "mean_token_accuracy": 0.8729922890663147,
305
+ "num_tokens": 155374.0,
306
+ "step": 165
307
+ },
308
+ {
309
+ "epoch": 0.5789697743720732,
310
+ "grad_norm": 0.6251844167709351,
311
+ "learning_rate": 0.00016131968145620024,
312
+ "loss": 0.6556,
313
+ "mean_token_accuracy": 0.8770609870553017,
314
+ "num_tokens": 160068.0,
315
+ "step": 170
316
+ },
317
+ {
318
+ "epoch": 0.5959982971477225,
319
+ "grad_norm": 0.804166853427887,
320
+ "learning_rate": 0.00016018202502844143,
321
+ "loss": 0.6366,
322
+ "mean_token_accuracy": 0.8760894432663917,
323
+ "num_tokens": 164696.0,
324
+ "step": 175
325
+ },
326
+ {
327
+ "epoch": 0.6130268199233716,
328
+ "grad_norm": 0.7013877034187317,
329
+ "learning_rate": 0.0001590443686006826,
330
+ "loss": 0.6328,
331
+ "mean_token_accuracy": 0.8779815405607223,
332
+ "num_tokens": 169356.0,
333
+ "step": 180
334
+ },
335
+ {
336
+ "epoch": 0.6300553426990209,
337
+ "grad_norm": 1.0623070001602173,
338
+ "learning_rate": 0.0001579067121729238,
339
+ "loss": 0.6734,
340
+ "mean_token_accuracy": 0.8710577815771103,
341
+ "num_tokens": 174041.0,
342
+ "step": 185
343
+ },
344
+ {
345
+ "epoch": 0.6470838654746701,
346
+ "grad_norm": 0.7858535647392273,
347
+ "learning_rate": 0.00015676905574516496,
348
+ "loss": 0.6775,
349
+ "mean_token_accuracy": 0.8692880481481552,
350
+ "num_tokens": 178858.0,
351
+ "step": 190
352
+ },
353
+ {
354
+ "epoch": 0.6641123882503193,
355
+ "grad_norm": 0.8943309187889099,
356
+ "learning_rate": 0.00015563139931740617,
357
+ "loss": 0.6874,
358
+ "mean_token_accuracy": 0.868885512650013,
359
+ "num_tokens": 183669.0,
360
+ "step": 195
361
+ },
362
+ {
363
+ "epoch": 0.6811409110259685,
364
+ "grad_norm": 0.5898745656013489,
365
+ "learning_rate": 0.00015449374288964733,
366
+ "loss": 0.6907,
367
+ "mean_token_accuracy": 0.8661940798163414,
368
+ "num_tokens": 188473.0,
369
+ "step": 200
370
+ },
371
+ {
372
+ "epoch": 0.6981694338016177,
373
+ "grad_norm": 0.6333857774734497,
374
+ "learning_rate": 0.00015335608646188854,
375
+ "loss": 0.6129,
376
+ "mean_token_accuracy": 0.8817986205220223,
377
+ "num_tokens": 193171.0,
378
+ "step": 205
379
+ },
380
+ {
381
+ "epoch": 0.7151979565772669,
382
+ "grad_norm": 0.5913947820663452,
383
+ "learning_rate": 0.0001522184300341297,
384
+ "loss": 0.5896,
385
+ "mean_token_accuracy": 0.8822762459516525,
386
+ "num_tokens": 197817.0,
387
+ "step": 210
388
+ },
389
+ {
390
+ "epoch": 0.7322264793529162,
391
+ "grad_norm": 0.6990242004394531,
392
+ "learning_rate": 0.00015108077360637088,
393
+ "loss": 0.6512,
394
+ "mean_token_accuracy": 0.8739180400967598,
395
+ "num_tokens": 202556.0,
396
+ "step": 215
397
+ },
398
+ {
399
+ "epoch": 0.7492550021285653,
400
+ "grad_norm": 0.6869048476219177,
401
+ "learning_rate": 0.00014994311717861207,
402
+ "loss": 0.7025,
403
+ "mean_token_accuracy": 0.8662877783179284,
404
+ "num_tokens": 207294.0,
405
+ "step": 220
406
+ },
407
+ {
408
+ "epoch": 0.7662835249042146,
409
+ "grad_norm": 0.5135166049003601,
410
+ "learning_rate": 0.00014880546075085325,
411
+ "loss": 0.6382,
412
+ "mean_token_accuracy": 0.8849207311868668,
413
+ "num_tokens": 211927.0,
414
+ "step": 225
415
+ },
416
+ {
417
+ "epoch": 0.7833120476798637,
418
+ "grad_norm": 0.6304216980934143,
419
+ "learning_rate": 0.00014766780432309444,
420
+ "loss": 0.6834,
421
+ "mean_token_accuracy": 0.8688049465417862,
422
+ "num_tokens": 216626.0,
423
+ "step": 230
424
+ },
425
+ {
426
+ "epoch": 0.800340570455513,
427
+ "grad_norm": 0.6879922151565552,
428
+ "learning_rate": 0.00014653014789533562,
429
+ "loss": 0.6902,
430
+ "mean_token_accuracy": 0.8655798360705376,
431
+ "num_tokens": 221432.0,
432
+ "step": 235
433
+ },
434
+ {
435
+ "epoch": 0.8173690932311622,
436
+ "grad_norm": 0.6433548331260681,
437
+ "learning_rate": 0.0001453924914675768,
438
+ "loss": 0.6129,
439
+ "mean_token_accuracy": 0.8795880794525146,
440
+ "num_tokens": 226022.0,
441
+ "step": 240
442
+ },
443
+ {
444
+ "epoch": 0.8343976160068114,
445
+ "grad_norm": 0.7876724600791931,
446
+ "learning_rate": 0.000144254835039818,
447
+ "loss": 0.6441,
448
+ "mean_token_accuracy": 0.8729524433612823,
449
+ "num_tokens": 230692.0,
450
+ "step": 245
451
+ },
452
+ {
453
+ "epoch": 0.8514261387824607,
454
+ "grad_norm": 0.6494749188423157,
455
+ "learning_rate": 0.00014311717861205915,
456
+ "loss": 0.7033,
457
+ "mean_token_accuracy": 0.8632469072937965,
458
+ "num_tokens": 235400.0,
459
+ "step": 250
460
+ },
461
+ {
462
+ "epoch": 0.8684546615581098,
463
+ "grad_norm": 0.6332300305366516,
464
+ "learning_rate": 0.00014197952218430036,
465
+ "loss": 0.5947,
466
+ "mean_token_accuracy": 0.8860528379678726,
467
+ "num_tokens": 239997.0,
468
+ "step": 255
469
+ },
470
+ {
471
+ "epoch": 0.885483184333759,
472
+ "grad_norm": 0.7144895195960999,
473
+ "learning_rate": 0.00014084186575654152,
474
+ "loss": 0.649,
475
+ "mean_token_accuracy": 0.8745664536952973,
476
+ "num_tokens": 244704.0,
477
+ "step": 260
478
+ },
479
+ {
480
+ "epoch": 0.9025117071094083,
481
+ "grad_norm": 0.5460124015808105,
482
+ "learning_rate": 0.00013970420932878273,
483
+ "loss": 0.6622,
484
+ "mean_token_accuracy": 0.8692788198590279,
485
+ "num_tokens": 249428.0,
486
+ "step": 265
487
+ },
488
+ {
489
+ "epoch": 0.9195402298850575,
490
+ "grad_norm": 0.65619295835495,
491
+ "learning_rate": 0.0001385665529010239,
492
+ "loss": 0.657,
493
+ "mean_token_accuracy": 0.8737826406955719,
494
+ "num_tokens": 254150.0,
495
+ "step": 270
496
+ },
497
+ {
498
+ "epoch": 0.9365687526607067,
499
+ "grad_norm": 0.8474870324134827,
500
+ "learning_rate": 0.0001374288964732651,
501
+ "loss": 0.6607,
502
+ "mean_token_accuracy": 0.8756056800484657,
503
+ "num_tokens": 258826.0,
504
+ "step": 275
505
+ },
506
+ {
507
+ "epoch": 0.9535972754363559,
508
+ "grad_norm": 0.6054229736328125,
509
+ "learning_rate": 0.00013629124004550626,
510
+ "loss": 0.6526,
511
+ "mean_token_accuracy": 0.8718441724777222,
512
+ "num_tokens": 263524.0,
513
+ "step": 280
514
+ },
515
+ {
516
+ "epoch": 0.9706257982120051,
517
+ "grad_norm": 0.6568702459335327,
518
+ "learning_rate": 0.00013515358361774744,
519
+ "loss": 0.6174,
520
+ "mean_token_accuracy": 0.881709736585617,
521
+ "num_tokens": 268179.0,
522
+ "step": 285
523
+ },
524
+ {
525
+ "epoch": 0.9876543209876543,
526
+ "grad_norm": 0.7518045902252197,
527
+ "learning_rate": 0.00013401592718998863,
528
+ "loss": 0.5896,
529
+ "mean_token_accuracy": 0.885109031200409,
530
+ "num_tokens": 272803.0,
531
+ "step": 290
532
+ },
533
+ {
534
+ "epoch": 1.0046828437633035,
535
+ "grad_norm": 0.5392197370529175,
536
+ "learning_rate": 0.00013287827076222981,
537
+ "loss": 0.6753,
538
+ "mean_token_accuracy": 0.8788385137915611,
539
+ "num_tokens": 277527.0,
540
+ "step": 295
541
+ },
542
+ {
543
+ "epoch": 1.0217113665389528,
544
+ "grad_norm": 0.5845906734466553,
545
+ "learning_rate": 0.000131740614334471,
546
+ "loss": 0.5237,
547
+ "mean_token_accuracy": 0.8938747227191925,
548
+ "num_tokens": 282199.0,
549
+ "step": 300
550
+ },
551
+ {
552
+ "epoch": 1.038739889314602,
553
+ "grad_norm": 0.6392928957939148,
554
+ "learning_rate": 0.00013060295790671218,
555
+ "loss": 0.4973,
556
+ "mean_token_accuracy": 0.8982622623443604,
557
+ "num_tokens": 286951.0,
558
+ "step": 305
559
+ },
560
+ {
561
+ "epoch": 1.055768412090251,
562
+ "grad_norm": 0.5399300456047058,
563
+ "learning_rate": 0.00012946530147895337,
564
+ "loss": 0.5076,
565
+ "mean_token_accuracy": 0.9008002370595932,
566
+ "num_tokens": 291569.0,
567
+ "step": 310
568
+ },
569
+ {
570
+ "epoch": 1.0727969348659003,
571
+ "grad_norm": 0.6236026883125305,
572
+ "learning_rate": 0.00012832764505119455,
573
+ "loss": 0.5084,
574
+ "mean_token_accuracy": 0.8972577184438706,
575
+ "num_tokens": 296230.0,
576
+ "step": 315
577
+ },
578
+ {
579
+ "epoch": 1.0898254576415496,
580
+ "grad_norm": 0.7385813593864441,
581
+ "learning_rate": 0.0001271899886234357,
582
+ "loss": 0.5062,
583
+ "mean_token_accuracy": 0.8956585437059402,
584
+ "num_tokens": 301029.0,
585
+ "step": 320
586
+ },
587
+ {
588
+ "epoch": 1.1068539804171988,
589
+ "grad_norm": 0.7647150754928589,
590
+ "learning_rate": 0.00012605233219567692,
591
+ "loss": 0.5078,
592
+ "mean_token_accuracy": 0.8982979074120522,
593
+ "num_tokens": 305696.0,
594
+ "step": 325
595
+ },
596
+ {
597
+ "epoch": 1.123882503192848,
598
+ "grad_norm": 0.6433872580528259,
599
+ "learning_rate": 0.00012491467576791808,
600
+ "loss": 0.5215,
601
+ "mean_token_accuracy": 0.8974734947085381,
602
+ "num_tokens": 310343.0,
603
+ "step": 330
604
+ },
605
+ {
606
+ "epoch": 1.1409110259684971,
607
+ "grad_norm": 0.6470033526420593,
608
+ "learning_rate": 0.0001237770193401593,
609
+ "loss": 0.5261,
610
+ "mean_token_accuracy": 0.8938129872083664,
611
+ "num_tokens": 315097.0,
612
+ "step": 335
613
+ },
614
+ {
615
+ "epoch": 1.1579395487441464,
616
+ "grad_norm": 0.6738846302032471,
617
+ "learning_rate": 0.00012263936291240045,
618
+ "loss": 0.5277,
619
+ "mean_token_accuracy": 0.8924461513757705,
620
+ "num_tokens": 319861.0,
621
+ "step": 340
622
+ },
623
+ {
624
+ "epoch": 1.1749680715197957,
625
+ "grad_norm": 0.6639145016670227,
626
+ "learning_rate": 0.00012150170648464165,
627
+ "loss": 0.5127,
628
+ "mean_token_accuracy": 0.8926685571670532,
629
+ "num_tokens": 324544.0,
630
+ "step": 345
631
+ },
632
+ {
633
+ "epoch": 1.191996594295445,
634
+ "grad_norm": 0.7034420371055603,
635
+ "learning_rate": 0.00012036405005688282,
636
+ "loss": 0.51,
637
+ "mean_token_accuracy": 0.8971043467521668,
638
+ "num_tokens": 329302.0,
639
+ "step": 350
640
+ },
641
+ {
642
+ "epoch": 1.2090251170710942,
643
+ "grad_norm": 0.6675500273704529,
644
+ "learning_rate": 0.000119226393629124,
645
+ "loss": 0.5738,
646
+ "mean_token_accuracy": 0.8855719327926636,
647
+ "num_tokens": 334103.0,
648
+ "step": 355
649
+ },
650
+ {
651
+ "epoch": 1.2260536398467432,
652
+ "grad_norm": 0.6019395589828491,
653
+ "learning_rate": 0.00011808873720136519,
654
+ "loss": 0.476,
655
+ "mean_token_accuracy": 0.8989460453391075,
656
+ "num_tokens": 338666.0,
657
+ "step": 360
658
+ },
659
+ {
660
+ "epoch": 1.2430821626223925,
661
+ "grad_norm": 0.6599250435829163,
662
+ "learning_rate": 0.00011695108077360638,
663
+ "loss": 0.5178,
664
+ "mean_token_accuracy": 0.8887226998805999,
665
+ "num_tokens": 343333.0,
666
+ "step": 365
667
+ },
668
+ {
669
+ "epoch": 1.2601106853980417,
670
+ "grad_norm": 0.7334213852882385,
671
+ "learning_rate": 0.00011581342434584756,
672
+ "loss": 0.5378,
673
+ "mean_token_accuracy": 0.8895460113883018,
674
+ "num_tokens": 348092.0,
675
+ "step": 370
676
+ },
677
+ {
678
+ "epoch": 1.277139208173691,
679
+ "grad_norm": 0.7423357963562012,
680
+ "learning_rate": 0.00011467576791808873,
681
+ "loss": 0.5012,
682
+ "mean_token_accuracy": 0.8994292929768563,
683
+ "num_tokens": 352661.0,
684
+ "step": 375
685
+ },
686
+ {
687
+ "epoch": 1.29416773094934,
688
+ "grad_norm": 0.857515811920166,
689
+ "learning_rate": 0.00011353811149032993,
690
+ "loss": 0.507,
691
+ "mean_token_accuracy": 0.8979884222149849,
692
+ "num_tokens": 357330.0,
693
+ "step": 380
694
+ },
695
+ {
696
+ "epoch": 1.3111962537249893,
697
+ "grad_norm": 0.5656803250312805,
698
+ "learning_rate": 0.0001124004550625711,
699
+ "loss": 0.5009,
700
+ "mean_token_accuracy": 0.8934224143624305,
701
+ "num_tokens": 362020.0,
702
+ "step": 385
703
+ },
704
+ {
705
+ "epoch": 1.3282247765006385,
706
+ "grad_norm": 0.6634964942932129,
707
+ "learning_rate": 0.00011126279863481229,
708
+ "loss": 0.5414,
709
+ "mean_token_accuracy": 0.8910330131649971,
710
+ "num_tokens": 366728.0,
711
+ "step": 390
712
+ },
713
+ {
714
+ "epoch": 1.3452532992762878,
715
+ "grad_norm": 0.7004157304763794,
716
+ "learning_rate": 0.00011012514220705347,
717
+ "loss": 0.4922,
718
+ "mean_token_accuracy": 0.8992783546447753,
719
+ "num_tokens": 371381.0,
720
+ "step": 395
721
+ },
722
+ {
723
+ "epoch": 1.362281822051937,
724
+ "grad_norm": 0.6225594282150269,
725
+ "learning_rate": 0.00010898748577929466,
726
+ "loss": 0.5084,
727
+ "mean_token_accuracy": 0.8956901535391808,
728
+ "num_tokens": 376043.0,
729
+ "step": 400
730
+ }
731
+ ],
732
+ "logging_steps": 5,
733
+ "max_steps": 879,
734
+ "num_input_tokens_seen": 0,
735
+ "num_train_epochs": 3,
736
+ "save_steps": 200,
737
+ "stateful_callbacks": {
738
+ "TrainerControl": {
739
+ "args": {
740
+ "should_epoch_stop": false,
741
+ "should_evaluate": false,
742
+ "should_log": false,
743
+ "should_save": true,
744
+ "should_training_stop": false
745
+ },
746
+ "attributes": {}
747
+ }
748
+ },
749
+ "total_flos": 1.7027680650141696e+16,
750
+ "train_batch_size": 1,
751
+ "trial_name": null,
752
+ "trial_params": null
753
+ }
checkpoint-400/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc4e07dc6df6129e6d2045027becfa7300f4a8ae9e98a02f1c9d1066e93703ce
3
+ size 5624
checkpoint-600/README.md ADDED
@@ -0,0 +1,209 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: NousResearch/Hermes-3-Llama-3.1-8B
3
+ library_name: peft
4
+ pipeline_tag: text-generation
5
+ tags:
6
+ - base_model:adapter:NousResearch/Hermes-3-Llama-3.1-8B
7
+ - lora
8
+ - sft
9
+ - transformers
10
+ - trl
11
+ ---
12
+
13
+ # Model Card for Model ID
14
+
15
+ <!-- Provide a quick summary of what the model is/does. -->
16
+
17
+
18
+
19
+ ## Model Details
20
+
21
+ ### Model Description
22
+
23
+ <!-- Provide a longer summary of what this model is. -->
24
+
25
+
26
+
27
+ - **Developed by:** [More Information Needed]
28
+ - **Funded by [optional]:** [More Information Needed]
29
+ - **Shared by [optional]:** [More Information Needed]
30
+ - **Model type:** [More Information Needed]
31
+ - **Language(s) (NLP):** [More Information Needed]
32
+ - **License:** [More Information Needed]
33
+ - **Finetuned from model [optional]:** [More Information Needed]
34
+
35
+ ### Model Sources [optional]
36
+
37
+ <!-- Provide the basic links for the model. -->
38
+
39
+ - **Repository:** [More Information Needed]
40
+ - **Paper [optional]:** [More Information Needed]
41
+ - **Demo [optional]:** [More Information Needed]
42
+
43
+ ## Uses
44
+
45
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
46
+
47
+ ### Direct Use
48
+
49
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
50
+
51
+ [More Information Needed]
52
+
53
+ ### Downstream Use [optional]
54
+
55
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
56
+
57
+ [More Information Needed]
58
+
59
+ ### Out-of-Scope Use
60
+
61
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
62
+
63
+ [More Information Needed]
64
+
65
+ ## Bias, Risks, and Limitations
66
+
67
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
68
+
69
+ [More Information Needed]
70
+
71
+ ### Recommendations
72
+
73
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
74
+
75
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
76
+
77
+ ## How to Get Started with the Model
78
+
79
+ Use the code below to get started with the model.
80
+
81
+ [More Information Needed]
82
+
83
+ ## Training Details
84
+
85
+ ### Training Data
86
+
87
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
88
+
89
+ [More Information Needed]
90
+
91
+ ### Training Procedure
92
+
93
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
94
+
95
+ #### Preprocessing [optional]
96
+
97
+ [More Information Needed]
98
+
99
+
100
+ #### Training Hyperparameters
101
+
102
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
103
+
104
+ #### Speeds, Sizes, Times [optional]
105
+
106
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
107
+
108
+ [More Information Needed]
109
+
110
+ ## Evaluation
111
+
112
+ <!-- This section describes the evaluation protocols and provides the results. -->
113
+
114
+ ### Testing Data, Factors & Metrics
115
+
116
+ #### Testing Data
117
+
118
+ <!-- This should link to a Dataset Card if possible. -->
119
+
120
+ [More Information Needed]
121
+
122
+ #### Factors
123
+
124
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
125
+
126
+ [More Information Needed]
127
+
128
+ #### Metrics
129
+
130
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
131
+
132
+ [More Information Needed]
133
+
134
+ ### Results
135
+
136
+ [More Information Needed]
137
+
138
+ #### Summary
139
+
140
+
141
+
142
+ ## Model Examination [optional]
143
+
144
+ <!-- Relevant interpretability work for the model goes here -->
145
+
146
+ [More Information Needed]
147
+
148
+ ## Environmental Impact
149
+
150
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
151
+
152
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
153
+
154
+ - **Hardware Type:** [More Information Needed]
155
+ - **Hours used:** [More Information Needed]
156
+ - **Cloud Provider:** [More Information Needed]
157
+ - **Compute Region:** [More Information Needed]
158
+ - **Carbon Emitted:** [More Information Needed]
159
+
160
+ ## Technical Specifications [optional]
161
+
162
+ ### Model Architecture and Objective
163
+
164
+ [More Information Needed]
165
+
166
+ ### Compute Infrastructure
167
+
168
+ [More Information Needed]
169
+
170
+ #### Hardware
171
+
172
+ [More Information Needed]
173
+
174
+ #### Software
175
+
176
+ [More Information Needed]
177
+
178
+ ## Citation [optional]
179
+
180
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
181
+
182
+ **BibTeX:**
183
+
184
+ [More Information Needed]
185
+
186
+ **APA:**
187
+
188
+ [More Information Needed]
189
+
190
+ ## Glossary [optional]
191
+
192
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
193
+
194
+ [More Information Needed]
195
+
196
+ ## More Information [optional]
197
+
198
+ [More Information Needed]
199
+
200
+ ## Model Card Authors [optional]
201
+
202
+ [More Information Needed]
203
+
204
+ ## Model Card Contact
205
+
206
+ [More Information Needed]
207
+ ### Framework versions
208
+
209
+ - PEFT 0.20.0
checkpoint-600/adapter_config.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alora_invocation_tokens": null,
3
+ "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": null,
6
+ "base_model_name_or_path": "NousResearch/Hermes-3-Llama-3.1-8B",
7
+ "bias": "none",
8
+ "corda_config": null,
9
+ "ensure_weight_tying": false,
10
+ "eva_config": null,
11
+ "exclude_modules": null,
12
+ "fan_in_fan_out": false,
13
+ "inference_mode": true,
14
+ "init_lora_weights": true,
15
+ "layer_replication": null,
16
+ "layers_pattern": null,
17
+ "layers_to_transform": null,
18
+ "loftq_config": {},
19
+ "lora_alpha": 32,
20
+ "lora_bias": false,
21
+ "lora_dropout": 0.05,
22
+ "lora_ga_config": null,
23
+ "megatron_config": null,
24
+ "megatron_core": "megatron.core",
25
+ "modules_to_save": null,
26
+ "monteclora_config": null,
27
+ "peft_type": "LORA",
28
+ "peft_version": "0.20.0",
29
+ "qalora_group_size": 16,
30
+ "r": 16,
31
+ "rank_pattern": {},
32
+ "revision": null,
33
+ "target_modules": [
34
+ "v_proj",
35
+ "q_proj",
36
+ "k_proj",
37
+ "down_proj",
38
+ "up_proj",
39
+ "gate_proj",
40
+ "o_proj"
41
+ ],
42
+ "target_parameters": null,
43
+ "task_type": "CAUSAL_LM",
44
+ "trainable_token_indices": null,
45
+ "use_bdlora": null,
46
+ "use_dora": false,
47
+ "use_qalora": false,
48
+ "use_rslora": false,
49
+ "velora_config": null
50
+ }
checkpoint-600/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f507d4abd7010e4a5130e20dd410de849fbd9c5df5116d8c42b121ce6084b10
3
+ size 167832240
checkpoint-600/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b21d3ba4f3589798d054250c59c9e7db0483addbff8261bcb5722b7ba517fc48
3
+ size 85728276
checkpoint-600/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5c778379c8bd89d29c7155c9f3c8011bb8e7d97afcc65976304bce4dcfefa37
3
+ size 14244
checkpoint-600/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7dd96493eebbb35a30ee240cfe1ad8f98b67771a20ddafde87bd6093f71d27bb
3
+ size 1064
checkpoint-600/special_tokens_map.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|im_end|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|im_end|>"
17
+ }
checkpoint-600/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14b5e679cb69af62e14c3b98d346177bd4137d882a44f87dec9efec982b01a05
3
+ size 17209403
checkpoint-600/tokenizer_config.json ADDED
@@ -0,0 +1,2072 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<tool_call>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": false
26
+ },
27
+ "128003": {
28
+ "content": "<tool_response>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": false
34
+ },
35
+ "128004": {
36
+ "content": "<|finetune_right_pad_id|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_2|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128006": {
52
+ "content": "<|start_header_id|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "128007": {
60
+ "content": "<|end_header_id|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "128008": {
68
+ "content": "<|eom_id|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "128009": {
76
+ "content": "<|eot_id|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "128010": {
84
+ "content": "<|python_tag|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<tools>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": false
98
+ },
99
+ "128012": {
100
+ "content": "</tools>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": false
106
+ },
107
+ "128013": {
108
+ "content": "</tool_call>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": false
114
+ },
115
+ "128014": {
116
+ "content": "</tool_response>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": false
122
+ },
123
+ "128015": {
124
+ "content": "<schema>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": false
130
+ },
131
+ "128016": {
132
+ "content": "</schema>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": false
138
+ },
139
+ "128017": {
140
+ "content": "<scratch_pad>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": false
146
+ },
147
+ "128018": {
148
+ "content": "</scratch_pad>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": false
154
+ },
155
+ "128019": {
156
+ "content": "<SCRATCHPAD>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": false
162
+ },
163
+ "128020": {
164
+ "content": "</SCRATCHPAD>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": false
170
+ },
171
+ "128021": {
172
+ "content": "<REASONING>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": false
178
+ },
179
+ "128022": {
180
+ "content": "</REASONING>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": false
186
+ },
187
+ "128023": {
188
+ "content": "<INNER_MONOLOGUE>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": false
194
+ },
195
+ "128024": {
196
+ "content": "</INNER_MONOLOGUE>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": false
202
+ },
203
+ "128025": {
204
+ "content": "<PLAN>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": false
210
+ },
211
+ "128026": {
212
+ "content": "</PLAN>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": false
218
+ },
219
+ "128027": {
220
+ "content": "<EXECUTION>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": false
226
+ },
227
+ "128028": {
228
+ "content": "</EXECUTION>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": false
234
+ },
235
+ "128029": {
236
+ "content": "<REFLECTION>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": false
242
+ },
243
+ "128030": {
244
+ "content": "</REFLECTION>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": false
250
+ },
251
+ "128031": {
252
+ "content": "<THINKING>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": false
258
+ },
259
+ "128032": {
260
+ "content": "</THINKING>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": false
266
+ },
267
+ "128033": {
268
+ "content": "<SOLUTION>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": false
274
+ },
275
+ "128034": {
276
+ "content": "</SOLUTION>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": false
282
+ },
283
+ "128035": {
284
+ "content": "<EXPLANATION>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": false
290
+ },
291
+ "128036": {
292
+ "content": "</EXPLANATION>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": false
298
+ },
299
+ "128037": {
300
+ "content": "<UNIT_TEST>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": false
306
+ },
307
+ "128038": {
308
+ "content": "</UNIT_TEST>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": false
314
+ },
315
+ "128039": {
316
+ "content": "<|im_start|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": false
322
+ },
323
+ "128040": {
324
+ "content": "<|im_end|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_33|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_34|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_35|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_36|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_37|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_38|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_39|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_40|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_41|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_42|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_43|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_44|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_45|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_46|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_47|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_48|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_49|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_50|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_51|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_52|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_53|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_54|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_55|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_56|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_57|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_58|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_59|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_60|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_61|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_62|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_63|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_64|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_65|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_66|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_67|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_68|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_69|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_70|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_71|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_72|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_73|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_74|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_75|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_76|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_77|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_78|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_79|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_80|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_81|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_82|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_83|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_84|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_85|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_86|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_87|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_88|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_89|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_90|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_91|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_92|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_93|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_94|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_95|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_96|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_97|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_98|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_99|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_100|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_101|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_102|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_103|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_104|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_105|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_106|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_107|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_108|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_109|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_110|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_111|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_112|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_113|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_114|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_115|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_116|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_117|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_118|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_119|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_120|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_121|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_122|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_123|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_124|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_125|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_126|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_127|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_128|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_129|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_130|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_131|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_132|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_133|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_134|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_135|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_136|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_137|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_138|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_139|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_140|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_141|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_142|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_143|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_144|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_145|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_146|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_147|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_148|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_149|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_150|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_151|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_152|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_153|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_154|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_155|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_156|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_157|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_158|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_159|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_160|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_161|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_162|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_163|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_164|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_165|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_166|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_167|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_168|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_169|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_170|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_171|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_172|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_173|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_174|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_175|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_176|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_177|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_178|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_179|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_180|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_181|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_182|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_183|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_184|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_185|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_186|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_187|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_188|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_189|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_190|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_191|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_192|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_193|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_194|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_195|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_196|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_197|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_198|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_199|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_200|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_201|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_202|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_203|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_204|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_205|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_206|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_207|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_208|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_209|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_210|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_211|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_212|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_213|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_214|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_215|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_216|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_217|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_218|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_219|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_220|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_221|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_222|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_223|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_224|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_225|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_226|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_227|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_228|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_229|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_230|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_231|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_232|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_233|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_234|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_235|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_236|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_237|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_238|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_239|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_240|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_241|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_242|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_243|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_244|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_245|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_246|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_247|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ }
2051
+ },
2052
+ "bos_token": "<|begin_of_text|>",
2053
+ "chat_template": [
2054
+ {
2055
+ "name": "default",
2056
+ "template": "{{bos_token}}{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}"
2057
+ },
2058
+ {
2059
+ "name": "tool_use",
2060
+ "template": "{%- macro json_to_python_type(json_spec) %}\n{%- set basic_type_map = {\n \"string\": \"str\",\n \"number\": \"float\",\n \"integer\": \"int\",\n \"boolean\": \"bool\"\n} %}\n\n{%- if basic_type_map[json_spec.type] is defined %}\n {{- basic_type_map[json_spec.type] }}\n{%- elif json_spec.type == \"array\" %}\n {{- \"list[\" + json_to_python_type(json_spec|items) + \"]\"}}\n{%- elif json_spec.type == \"object\" %}\n {%- if json_spec.additionalProperties is defined %}\n {{- \"dict[str, \" + json_to_python_type(json_spec.additionalProperties) + ']'}}\n {%- else %}\n {{- \"dict\" }}\n {%- endif %}\n{%- elif json_spec.type is iterable %}\n {{- \"Union[\" }}\n {%- for t in json_spec.type %}\n {{- json_to_python_type({\"type\": t}) }}\n {%- if not loop.last %}\n {{- \",\" }} \n {%- endif %}\n {%- endfor %}\n {{- \"]\" }}\n{%- else %}\n {{- \"Any\" }}\n{%- endif %}\n{%- endmacro %}\n\n\n{{- bos_token }}\n{{- '<|im_start|>system\n' }}\n{{- \"You are a function calling AI model. You are provided with function signatures within <tools></tools> XML tags. You may call one or more functions to assist with the user query. Don't make assumptions about what values to plug into functions. Here are the available tools: <tools> \" }}\n{%- for tool in tools %}\n {%- if tool.function is defined %}\n {%- set tool = tool.function %}\n {%- endif %}\n {{- '{\"type\": \"function\", \"function\": ' }}\n {{- '{\"name\": \"' + tool.name + '\", ' }}\n {{- '\"description\": \"' + tool.name + '(' }}\n {%- for param_name, param_fields in tool.parameters.properties|items %}\n {{- param_name + \": \" + json_to_python_type(param_fields) }}\n {%- if not loop.last %}\n {{- \", \" }}\n {%- endif %}\n {%- endfor %}\n {{- \")\" }}\n {%- if tool.return is defined %}\n {{- \" -> \" + json_to_python_type(tool.return) }}\n {%- endif %}\n {{- \" - \" + tool.description + \"\n\n\" }}\n {%- for param_name, param_fields in tool.parameters.properties|items %}\n {%- if loop.first %}\n {{- \" Args:\n\" }}\n {%- endif %}\n {{- \" \" + param_name + \"(\" + json_to_python_type(param_fields) + \"): \" + param_fields.description|trim }}\n {%- endfor %}\n {%- if tool.return is defined and tool.return.description is defined %}\n {{- \"\n Returns:\n \" + tool.return.description }}\n {%- endif %}\n {{- '\"' }}\n {{- ', \"parameters\": ' }}\n {%- if tool.parameters.properties | length == 0 %}\n {{- \"{}\" }}\n {%- else %}\n {{- tool.parameters|tojson }}\n {%- endif %}\n {{- \"}\" }}\n {%- if not loop.last %}\n {{- \"\n\" }}\n {%- endif %}\n{%- endfor %}\n{{- \" </tools>\" }}\n{{- 'Use the following pydantic model json schema for each tool call you will make: {\"properties\": {\"name\": {\"title\": \"Name\", \"type\": \"string\"}, \"arguments\": {\"title\": \"Arguments\", \"type\": \"object\"}}, \"required\": [\"name\", \"arguments\"], \"title\": \"FunctionCall\", \"type\": \"object\"}}\n' }}\n{{- \"For each function call return a json object with function name and arguments within <tool_call></tool_call> XML tags as follows:\n\" }}\n{{- \"<tool_call>\n\" }}\n{{- '{\"name\": <function-name>, \"arguments\": <args-dict>}\n' }}\n{{- '</tool_call><|im_end|>\n' }}\n{%- for message in messages %}\n {%- if message.role == \"user\" or message.role == \"system\" or (message.role == \"assistant\" and message.tool_calls is not defined) %}\n {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- for tool_call in message.tool_calls %}\n {{- '\n<tool_call>\n' }} {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '{' }}\n {{- '\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\"' }}\n {{- ', '}}\n {%- if tool_call.arguments is defined %}\n {{- '\"arguments\": ' }}\n {%- if tool_call.arguments is string %}\n {{- tool_call.arguments }}\n {%- else %}\n {{- tool_call.arguments|tojson }}\n {%- endif %}\n {%- endif %}\n {{- '}' }}\n {{- '\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.previtem and loop.previtem.role != \"tool\" %}\n {{- '<|im_start|>tool\n' }}\n {%- endif %}\n {{- '<tool_response>\n' }}\n {{- message.content }}\n {%- if not loop.last %}\n {{- '\n</tool_response>\n' }}\n {%- else %}\n {{- '\n</tool_response>' }}\n {%- endif %}\n {%- if not loop.last and loop.nextitem.role != \"tool\" %}\n {{- '<|im_end|>' }}\n {%- elif loop.last %}\n {{- '<|im_end|>' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\n' }}\n{%- endif %}\n"
2061
+ }
2062
+ ],
2063
+ "clean_up_tokenization_spaces": true,
2064
+ "eos_token": "<|im_end|>",
2065
+ "model_input_names": [
2066
+ "input_ids",
2067
+ "attention_mask"
2068
+ ],
2069
+ "model_max_length": 131072,
2070
+ "pad_token": "<|im_end|>",
2071
+ "tokenizer_class": "PreTrainedTokenizerFast"
2072
+ }
checkpoint-600/trainer_state.json ADDED
@@ -0,0 +1,1113 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.0434227330779056,
5
+ "eval_steps": 500,
6
+ "global_step": 600,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.017028522775649212,
13
+ "grad_norm": 6.522716999053955,
14
+ "learning_rate": 0.0001988623435722412,
15
+ "loss": 2.7211,
16
+ "mean_token_accuracy": 0.5789041496813297,
17
+ "num_tokens": 4727.0,
18
+ "step": 5
19
+ },
20
+ {
21
+ "epoch": 0.034057045551298425,
22
+ "grad_norm": 1.0070050954818726,
23
+ "learning_rate": 0.00019772468714448238,
24
+ "loss": 0.9998,
25
+ "mean_token_accuracy": 0.8499793156981468,
26
+ "num_tokens": 9471.0,
27
+ "step": 10
28
+ },
29
+ {
30
+ "epoch": 0.05108556832694764,
31
+ "grad_norm": 0.7373425960540771,
32
+ "learning_rate": 0.00019658703071672356,
33
+ "loss": 0.8303,
34
+ "mean_token_accuracy": 0.8681916877627373,
35
+ "num_tokens": 14013.0,
36
+ "step": 15
37
+ },
38
+ {
39
+ "epoch": 0.06811409110259685,
40
+ "grad_norm": 0.8468236327171326,
41
+ "learning_rate": 0.00019544937428896475,
42
+ "loss": 0.8404,
43
+ "mean_token_accuracy": 0.8622620105743408,
44
+ "num_tokens": 18725.0,
45
+ "step": 20
46
+ },
47
+ {
48
+ "epoch": 0.08514261387824607,
49
+ "grad_norm": 0.8178804516792297,
50
+ "learning_rate": 0.00019431171786120593,
51
+ "loss": 0.9073,
52
+ "mean_token_accuracy": 0.8524447843432427,
53
+ "num_tokens": 23497.0,
54
+ "step": 25
55
+ },
56
+ {
57
+ "epoch": 0.10217113665389528,
58
+ "grad_norm": 0.890177309513092,
59
+ "learning_rate": 0.00019317406143344712,
60
+ "loss": 0.8029,
61
+ "mean_token_accuracy": 0.8642359614372254,
62
+ "num_tokens": 28192.0,
63
+ "step": 30
64
+ },
65
+ {
66
+ "epoch": 0.11919965942954448,
67
+ "grad_norm": 1.0545469522476196,
68
+ "learning_rate": 0.0001920364050056883,
69
+ "loss": 0.7458,
70
+ "mean_token_accuracy": 0.8732351213693619,
71
+ "num_tokens": 32805.0,
72
+ "step": 35
73
+ },
74
+ {
75
+ "epoch": 0.1362281822051937,
76
+ "grad_norm": 1.0384492874145508,
77
+ "learning_rate": 0.00019089874857792946,
78
+ "loss": 0.9235,
79
+ "mean_token_accuracy": 0.8408558666706085,
80
+ "num_tokens": 37714.0,
81
+ "step": 40
82
+ },
83
+ {
84
+ "epoch": 0.1532567049808429,
85
+ "grad_norm": 0.6860374808311462,
86
+ "learning_rate": 0.00018976109215017067,
87
+ "loss": 0.7623,
88
+ "mean_token_accuracy": 0.8656536340713501,
89
+ "num_tokens": 42429.0,
90
+ "step": 45
91
+ },
92
+ {
93
+ "epoch": 0.17028522775649213,
94
+ "grad_norm": 0.7284501791000366,
95
+ "learning_rate": 0.00018862343572241183,
96
+ "loss": 0.7588,
97
+ "mean_token_accuracy": 0.8688850715756417,
98
+ "num_tokens": 47099.0,
99
+ "step": 50
100
+ },
101
+ {
102
+ "epoch": 0.18731375053214133,
103
+ "grad_norm": 0.8899862170219421,
104
+ "learning_rate": 0.00018748577929465302,
105
+ "loss": 0.7065,
106
+ "mean_token_accuracy": 0.8717748820781708,
107
+ "num_tokens": 51795.0,
108
+ "step": 55
109
+ },
110
+ {
111
+ "epoch": 0.20434227330779056,
112
+ "grad_norm": 0.5350505709648132,
113
+ "learning_rate": 0.0001863481228668942,
114
+ "loss": 0.6696,
115
+ "mean_token_accuracy": 0.8851396456360817,
116
+ "num_tokens": 56369.0,
117
+ "step": 60
118
+ },
119
+ {
120
+ "epoch": 0.22137079608343976,
121
+ "grad_norm": 0.6087013483047485,
122
+ "learning_rate": 0.0001852104664391354,
123
+ "loss": 0.7204,
124
+ "mean_token_accuracy": 0.8682332798838616,
125
+ "num_tokens": 61018.0,
126
+ "step": 65
127
+ },
128
+ {
129
+ "epoch": 0.23839931885908897,
130
+ "grad_norm": 0.7879019379615784,
131
+ "learning_rate": 0.00018407281001137657,
132
+ "loss": 0.7692,
133
+ "mean_token_accuracy": 0.8653983056545258,
134
+ "num_tokens": 65741.0,
135
+ "step": 70
136
+ },
137
+ {
138
+ "epoch": 0.2554278416347382,
139
+ "grad_norm": 0.6546444296836853,
140
+ "learning_rate": 0.00018293515358361776,
141
+ "loss": 0.7119,
142
+ "mean_token_accuracy": 0.8726310178637504,
143
+ "num_tokens": 70425.0,
144
+ "step": 75
145
+ },
146
+ {
147
+ "epoch": 0.2724563644103874,
148
+ "grad_norm": 0.770902156829834,
149
+ "learning_rate": 0.00018179749715585894,
150
+ "loss": 0.7035,
151
+ "mean_token_accuracy": 0.8711811751127243,
152
+ "num_tokens": 75101.0,
153
+ "step": 80
154
+ },
155
+ {
156
+ "epoch": 0.2894848871860366,
157
+ "grad_norm": 0.8873187899589539,
158
+ "learning_rate": 0.00018065984072810013,
159
+ "loss": 0.7419,
160
+ "mean_token_accuracy": 0.8616803497076034,
161
+ "num_tokens": 79888.0,
162
+ "step": 85
163
+ },
164
+ {
165
+ "epoch": 0.3065134099616858,
166
+ "grad_norm": 0.7061370015144348,
167
+ "learning_rate": 0.0001795221843003413,
168
+ "loss": 0.66,
169
+ "mean_token_accuracy": 0.8744896531105042,
170
+ "num_tokens": 84562.0,
171
+ "step": 90
172
+ },
173
+ {
174
+ "epoch": 0.32354193273733506,
175
+ "grad_norm": 0.8232033252716064,
176
+ "learning_rate": 0.0001783845278725825,
177
+ "loss": 0.7403,
178
+ "mean_token_accuracy": 0.8659066379070282,
179
+ "num_tokens": 89238.0,
180
+ "step": 95
181
+ },
182
+ {
183
+ "epoch": 0.34057045551298426,
184
+ "grad_norm": 0.7313310503959656,
185
+ "learning_rate": 0.00017724687144482368,
186
+ "loss": 0.7157,
187
+ "mean_token_accuracy": 0.8661555901169777,
188
+ "num_tokens": 93987.0,
189
+ "step": 100
190
+ },
191
+ {
192
+ "epoch": 0.35759897828863346,
193
+ "grad_norm": 0.7119390964508057,
194
+ "learning_rate": 0.00017610921501706487,
195
+ "loss": 0.7016,
196
+ "mean_token_accuracy": 0.8678551658987999,
197
+ "num_tokens": 98722.0,
198
+ "step": 105
199
+ },
200
+ {
201
+ "epoch": 0.37462750106428266,
202
+ "grad_norm": 0.7126006484031677,
203
+ "learning_rate": 0.00017497155858930602,
204
+ "loss": 0.7009,
205
+ "mean_token_accuracy": 0.867291408777237,
206
+ "num_tokens": 103439.0,
207
+ "step": 110
208
+ },
209
+ {
210
+ "epoch": 0.39165602383993187,
211
+ "grad_norm": 0.6158230304718018,
212
+ "learning_rate": 0.00017383390216154724,
213
+ "loss": 0.7236,
214
+ "mean_token_accuracy": 0.8636128515005111,
215
+ "num_tokens": 108209.0,
216
+ "step": 115
217
+ },
218
+ {
219
+ "epoch": 0.4086845466155811,
220
+ "grad_norm": 0.6498322486877441,
221
+ "learning_rate": 0.0001726962457337884,
222
+ "loss": 0.6813,
223
+ "mean_token_accuracy": 0.8757071048021317,
224
+ "num_tokens": 112855.0,
225
+ "step": 120
226
+ },
227
+ {
228
+ "epoch": 0.4257130693912303,
229
+ "grad_norm": 0.6594287157058716,
230
+ "learning_rate": 0.0001715585893060296,
231
+ "loss": 0.7062,
232
+ "mean_token_accuracy": 0.8650311172008515,
233
+ "num_tokens": 117653.0,
234
+ "step": 125
235
+ },
236
+ {
237
+ "epoch": 0.4427415921668795,
238
+ "grad_norm": 0.7375237941741943,
239
+ "learning_rate": 0.00017042093287827076,
240
+ "loss": 0.6477,
241
+ "mean_token_accuracy": 0.8733970731496811,
242
+ "num_tokens": 122397.0,
243
+ "step": 130
244
+ },
245
+ {
246
+ "epoch": 0.45977011494252873,
247
+ "grad_norm": 0.5958442687988281,
248
+ "learning_rate": 0.00016928327645051198,
249
+ "loss": 0.691,
250
+ "mean_token_accuracy": 0.8681387722492218,
251
+ "num_tokens": 127136.0,
252
+ "step": 135
253
+ },
254
+ {
255
+ "epoch": 0.47679863771817793,
256
+ "grad_norm": 0.7407785654067993,
257
+ "learning_rate": 0.00016814562002275313,
258
+ "loss": 0.6477,
259
+ "mean_token_accuracy": 0.8752307429909706,
260
+ "num_tokens": 131833.0,
261
+ "step": 140
262
+ },
263
+ {
264
+ "epoch": 0.49382716049382713,
265
+ "grad_norm": 0.8190199732780457,
266
+ "learning_rate": 0.00016700796359499432,
267
+ "loss": 0.6608,
268
+ "mean_token_accuracy": 0.8762851104140281,
269
+ "num_tokens": 136441.0,
270
+ "step": 145
271
+ },
272
+ {
273
+ "epoch": 0.5108556832694764,
274
+ "grad_norm": 0.7571837306022644,
275
+ "learning_rate": 0.0001658703071672355,
276
+ "loss": 0.673,
277
+ "mean_token_accuracy": 0.8691665843129158,
278
+ "num_tokens": 141186.0,
279
+ "step": 150
280
+ },
281
+ {
282
+ "epoch": 0.5278842060451255,
283
+ "grad_norm": 0.6653426885604858,
284
+ "learning_rate": 0.0001647326507394767,
285
+ "loss": 0.7126,
286
+ "mean_token_accuracy": 0.8647830635309219,
287
+ "num_tokens": 145971.0,
288
+ "step": 155
289
+ },
290
+ {
291
+ "epoch": 0.5449127288207748,
292
+ "grad_norm": 0.7333567142486572,
293
+ "learning_rate": 0.00016359499431171787,
294
+ "loss": 0.6287,
295
+ "mean_token_accuracy": 0.878324082493782,
296
+ "num_tokens": 150669.0,
297
+ "step": 160
298
+ },
299
+ {
300
+ "epoch": 0.561941251596424,
301
+ "grad_norm": 0.8214460015296936,
302
+ "learning_rate": 0.00016245733788395906,
303
+ "loss": 0.6608,
304
+ "mean_token_accuracy": 0.8729922890663147,
305
+ "num_tokens": 155374.0,
306
+ "step": 165
307
+ },
308
+ {
309
+ "epoch": 0.5789697743720732,
310
+ "grad_norm": 0.6251844167709351,
311
+ "learning_rate": 0.00016131968145620024,
312
+ "loss": 0.6556,
313
+ "mean_token_accuracy": 0.8770609870553017,
314
+ "num_tokens": 160068.0,
315
+ "step": 170
316
+ },
317
+ {
318
+ "epoch": 0.5959982971477225,
319
+ "grad_norm": 0.804166853427887,
320
+ "learning_rate": 0.00016018202502844143,
321
+ "loss": 0.6366,
322
+ "mean_token_accuracy": 0.8760894432663917,
323
+ "num_tokens": 164696.0,
324
+ "step": 175
325
+ },
326
+ {
327
+ "epoch": 0.6130268199233716,
328
+ "grad_norm": 0.7013877034187317,
329
+ "learning_rate": 0.0001590443686006826,
330
+ "loss": 0.6328,
331
+ "mean_token_accuracy": 0.8779815405607223,
332
+ "num_tokens": 169356.0,
333
+ "step": 180
334
+ },
335
+ {
336
+ "epoch": 0.6300553426990209,
337
+ "grad_norm": 1.0623070001602173,
338
+ "learning_rate": 0.0001579067121729238,
339
+ "loss": 0.6734,
340
+ "mean_token_accuracy": 0.8710577815771103,
341
+ "num_tokens": 174041.0,
342
+ "step": 185
343
+ },
344
+ {
345
+ "epoch": 0.6470838654746701,
346
+ "grad_norm": 0.7858535647392273,
347
+ "learning_rate": 0.00015676905574516496,
348
+ "loss": 0.6775,
349
+ "mean_token_accuracy": 0.8692880481481552,
350
+ "num_tokens": 178858.0,
351
+ "step": 190
352
+ },
353
+ {
354
+ "epoch": 0.6641123882503193,
355
+ "grad_norm": 0.8943309187889099,
356
+ "learning_rate": 0.00015563139931740617,
357
+ "loss": 0.6874,
358
+ "mean_token_accuracy": 0.868885512650013,
359
+ "num_tokens": 183669.0,
360
+ "step": 195
361
+ },
362
+ {
363
+ "epoch": 0.6811409110259685,
364
+ "grad_norm": 0.5898745656013489,
365
+ "learning_rate": 0.00015449374288964733,
366
+ "loss": 0.6907,
367
+ "mean_token_accuracy": 0.8661940798163414,
368
+ "num_tokens": 188473.0,
369
+ "step": 200
370
+ },
371
+ {
372
+ "epoch": 0.6981694338016177,
373
+ "grad_norm": 0.6333857774734497,
374
+ "learning_rate": 0.00015335608646188854,
375
+ "loss": 0.6129,
376
+ "mean_token_accuracy": 0.8817986205220223,
377
+ "num_tokens": 193171.0,
378
+ "step": 205
379
+ },
380
+ {
381
+ "epoch": 0.7151979565772669,
382
+ "grad_norm": 0.5913947820663452,
383
+ "learning_rate": 0.0001522184300341297,
384
+ "loss": 0.5896,
385
+ "mean_token_accuracy": 0.8822762459516525,
386
+ "num_tokens": 197817.0,
387
+ "step": 210
388
+ },
389
+ {
390
+ "epoch": 0.7322264793529162,
391
+ "grad_norm": 0.6990242004394531,
392
+ "learning_rate": 0.00015108077360637088,
393
+ "loss": 0.6512,
394
+ "mean_token_accuracy": 0.8739180400967598,
395
+ "num_tokens": 202556.0,
396
+ "step": 215
397
+ },
398
+ {
399
+ "epoch": 0.7492550021285653,
400
+ "grad_norm": 0.6869048476219177,
401
+ "learning_rate": 0.00014994311717861207,
402
+ "loss": 0.7025,
403
+ "mean_token_accuracy": 0.8662877783179284,
404
+ "num_tokens": 207294.0,
405
+ "step": 220
406
+ },
407
+ {
408
+ "epoch": 0.7662835249042146,
409
+ "grad_norm": 0.5135166049003601,
410
+ "learning_rate": 0.00014880546075085325,
411
+ "loss": 0.6382,
412
+ "mean_token_accuracy": 0.8849207311868668,
413
+ "num_tokens": 211927.0,
414
+ "step": 225
415
+ },
416
+ {
417
+ "epoch": 0.7833120476798637,
418
+ "grad_norm": 0.6304216980934143,
419
+ "learning_rate": 0.00014766780432309444,
420
+ "loss": 0.6834,
421
+ "mean_token_accuracy": 0.8688049465417862,
422
+ "num_tokens": 216626.0,
423
+ "step": 230
424
+ },
425
+ {
426
+ "epoch": 0.800340570455513,
427
+ "grad_norm": 0.6879922151565552,
428
+ "learning_rate": 0.00014653014789533562,
429
+ "loss": 0.6902,
430
+ "mean_token_accuracy": 0.8655798360705376,
431
+ "num_tokens": 221432.0,
432
+ "step": 235
433
+ },
434
+ {
435
+ "epoch": 0.8173690932311622,
436
+ "grad_norm": 0.6433548331260681,
437
+ "learning_rate": 0.0001453924914675768,
438
+ "loss": 0.6129,
439
+ "mean_token_accuracy": 0.8795880794525146,
440
+ "num_tokens": 226022.0,
441
+ "step": 240
442
+ },
443
+ {
444
+ "epoch": 0.8343976160068114,
445
+ "grad_norm": 0.7876724600791931,
446
+ "learning_rate": 0.000144254835039818,
447
+ "loss": 0.6441,
448
+ "mean_token_accuracy": 0.8729524433612823,
449
+ "num_tokens": 230692.0,
450
+ "step": 245
451
+ },
452
+ {
453
+ "epoch": 0.8514261387824607,
454
+ "grad_norm": 0.6494749188423157,
455
+ "learning_rate": 0.00014311717861205915,
456
+ "loss": 0.7033,
457
+ "mean_token_accuracy": 0.8632469072937965,
458
+ "num_tokens": 235400.0,
459
+ "step": 250
460
+ },
461
+ {
462
+ "epoch": 0.8684546615581098,
463
+ "grad_norm": 0.6332300305366516,
464
+ "learning_rate": 0.00014197952218430036,
465
+ "loss": 0.5947,
466
+ "mean_token_accuracy": 0.8860528379678726,
467
+ "num_tokens": 239997.0,
468
+ "step": 255
469
+ },
470
+ {
471
+ "epoch": 0.885483184333759,
472
+ "grad_norm": 0.7144895195960999,
473
+ "learning_rate": 0.00014084186575654152,
474
+ "loss": 0.649,
475
+ "mean_token_accuracy": 0.8745664536952973,
476
+ "num_tokens": 244704.0,
477
+ "step": 260
478
+ },
479
+ {
480
+ "epoch": 0.9025117071094083,
481
+ "grad_norm": 0.5460124015808105,
482
+ "learning_rate": 0.00013970420932878273,
483
+ "loss": 0.6622,
484
+ "mean_token_accuracy": 0.8692788198590279,
485
+ "num_tokens": 249428.0,
486
+ "step": 265
487
+ },
488
+ {
489
+ "epoch": 0.9195402298850575,
490
+ "grad_norm": 0.65619295835495,
491
+ "learning_rate": 0.0001385665529010239,
492
+ "loss": 0.657,
493
+ "mean_token_accuracy": 0.8737826406955719,
494
+ "num_tokens": 254150.0,
495
+ "step": 270
496
+ },
497
+ {
498
+ "epoch": 0.9365687526607067,
499
+ "grad_norm": 0.8474870324134827,
500
+ "learning_rate": 0.0001374288964732651,
501
+ "loss": 0.6607,
502
+ "mean_token_accuracy": 0.8756056800484657,
503
+ "num_tokens": 258826.0,
504
+ "step": 275
505
+ },
506
+ {
507
+ "epoch": 0.9535972754363559,
508
+ "grad_norm": 0.6054229736328125,
509
+ "learning_rate": 0.00013629124004550626,
510
+ "loss": 0.6526,
511
+ "mean_token_accuracy": 0.8718441724777222,
512
+ "num_tokens": 263524.0,
513
+ "step": 280
514
+ },
515
+ {
516
+ "epoch": 0.9706257982120051,
517
+ "grad_norm": 0.6568702459335327,
518
+ "learning_rate": 0.00013515358361774744,
519
+ "loss": 0.6174,
520
+ "mean_token_accuracy": 0.881709736585617,
521
+ "num_tokens": 268179.0,
522
+ "step": 285
523
+ },
524
+ {
525
+ "epoch": 0.9876543209876543,
526
+ "grad_norm": 0.7518045902252197,
527
+ "learning_rate": 0.00013401592718998863,
528
+ "loss": 0.5896,
529
+ "mean_token_accuracy": 0.885109031200409,
530
+ "num_tokens": 272803.0,
531
+ "step": 290
532
+ },
533
+ {
534
+ "epoch": 1.0046828437633035,
535
+ "grad_norm": 0.5392197370529175,
536
+ "learning_rate": 0.00013287827076222981,
537
+ "loss": 0.6753,
538
+ "mean_token_accuracy": 0.8788385137915611,
539
+ "num_tokens": 277527.0,
540
+ "step": 295
541
+ },
542
+ {
543
+ "epoch": 1.0217113665389528,
544
+ "grad_norm": 0.5845906734466553,
545
+ "learning_rate": 0.000131740614334471,
546
+ "loss": 0.5237,
547
+ "mean_token_accuracy": 0.8938747227191925,
548
+ "num_tokens": 282199.0,
549
+ "step": 300
550
+ },
551
+ {
552
+ "epoch": 1.038739889314602,
553
+ "grad_norm": 0.6392928957939148,
554
+ "learning_rate": 0.00013060295790671218,
555
+ "loss": 0.4973,
556
+ "mean_token_accuracy": 0.8982622623443604,
557
+ "num_tokens": 286951.0,
558
+ "step": 305
559
+ },
560
+ {
561
+ "epoch": 1.055768412090251,
562
+ "grad_norm": 0.5399300456047058,
563
+ "learning_rate": 0.00012946530147895337,
564
+ "loss": 0.5076,
565
+ "mean_token_accuracy": 0.9008002370595932,
566
+ "num_tokens": 291569.0,
567
+ "step": 310
568
+ },
569
+ {
570
+ "epoch": 1.0727969348659003,
571
+ "grad_norm": 0.6236026883125305,
572
+ "learning_rate": 0.00012832764505119455,
573
+ "loss": 0.5084,
574
+ "mean_token_accuracy": 0.8972577184438706,
575
+ "num_tokens": 296230.0,
576
+ "step": 315
577
+ },
578
+ {
579
+ "epoch": 1.0898254576415496,
580
+ "grad_norm": 0.7385813593864441,
581
+ "learning_rate": 0.0001271899886234357,
582
+ "loss": 0.5062,
583
+ "mean_token_accuracy": 0.8956585437059402,
584
+ "num_tokens": 301029.0,
585
+ "step": 320
586
+ },
587
+ {
588
+ "epoch": 1.1068539804171988,
589
+ "grad_norm": 0.7647150754928589,
590
+ "learning_rate": 0.00012605233219567692,
591
+ "loss": 0.5078,
592
+ "mean_token_accuracy": 0.8982979074120522,
593
+ "num_tokens": 305696.0,
594
+ "step": 325
595
+ },
596
+ {
597
+ "epoch": 1.123882503192848,
598
+ "grad_norm": 0.6433872580528259,
599
+ "learning_rate": 0.00012491467576791808,
600
+ "loss": 0.5215,
601
+ "mean_token_accuracy": 0.8974734947085381,
602
+ "num_tokens": 310343.0,
603
+ "step": 330
604
+ },
605
+ {
606
+ "epoch": 1.1409110259684971,
607
+ "grad_norm": 0.6470033526420593,
608
+ "learning_rate": 0.0001237770193401593,
609
+ "loss": 0.5261,
610
+ "mean_token_accuracy": 0.8938129872083664,
611
+ "num_tokens": 315097.0,
612
+ "step": 335
613
+ },
614
+ {
615
+ "epoch": 1.1579395487441464,
616
+ "grad_norm": 0.6738846302032471,
617
+ "learning_rate": 0.00012263936291240045,
618
+ "loss": 0.5277,
619
+ "mean_token_accuracy": 0.8924461513757705,
620
+ "num_tokens": 319861.0,
621
+ "step": 340
622
+ },
623
+ {
624
+ "epoch": 1.1749680715197957,
625
+ "grad_norm": 0.6639145016670227,
626
+ "learning_rate": 0.00012150170648464165,
627
+ "loss": 0.5127,
628
+ "mean_token_accuracy": 0.8926685571670532,
629
+ "num_tokens": 324544.0,
630
+ "step": 345
631
+ },
632
+ {
633
+ "epoch": 1.191996594295445,
634
+ "grad_norm": 0.7034420371055603,
635
+ "learning_rate": 0.00012036405005688282,
636
+ "loss": 0.51,
637
+ "mean_token_accuracy": 0.8971043467521668,
638
+ "num_tokens": 329302.0,
639
+ "step": 350
640
+ },
641
+ {
642
+ "epoch": 1.2090251170710942,
643
+ "grad_norm": 0.6675500273704529,
644
+ "learning_rate": 0.000119226393629124,
645
+ "loss": 0.5738,
646
+ "mean_token_accuracy": 0.8855719327926636,
647
+ "num_tokens": 334103.0,
648
+ "step": 355
649
+ },
650
+ {
651
+ "epoch": 1.2260536398467432,
652
+ "grad_norm": 0.6019395589828491,
653
+ "learning_rate": 0.00011808873720136519,
654
+ "loss": 0.476,
655
+ "mean_token_accuracy": 0.8989460453391075,
656
+ "num_tokens": 338666.0,
657
+ "step": 360
658
+ },
659
+ {
660
+ "epoch": 1.2430821626223925,
661
+ "grad_norm": 0.6599250435829163,
662
+ "learning_rate": 0.00011695108077360638,
663
+ "loss": 0.5178,
664
+ "mean_token_accuracy": 0.8887226998805999,
665
+ "num_tokens": 343333.0,
666
+ "step": 365
667
+ },
668
+ {
669
+ "epoch": 1.2601106853980417,
670
+ "grad_norm": 0.7334213852882385,
671
+ "learning_rate": 0.00011581342434584756,
672
+ "loss": 0.5378,
673
+ "mean_token_accuracy": 0.8895460113883018,
674
+ "num_tokens": 348092.0,
675
+ "step": 370
676
+ },
677
+ {
678
+ "epoch": 1.277139208173691,
679
+ "grad_norm": 0.7423357963562012,
680
+ "learning_rate": 0.00011467576791808873,
681
+ "loss": 0.5012,
682
+ "mean_token_accuracy": 0.8994292929768563,
683
+ "num_tokens": 352661.0,
684
+ "step": 375
685
+ },
686
+ {
687
+ "epoch": 1.29416773094934,
688
+ "grad_norm": 0.857515811920166,
689
+ "learning_rate": 0.00011353811149032993,
690
+ "loss": 0.507,
691
+ "mean_token_accuracy": 0.8979884222149849,
692
+ "num_tokens": 357330.0,
693
+ "step": 380
694
+ },
695
+ {
696
+ "epoch": 1.3111962537249893,
697
+ "grad_norm": 0.5656803250312805,
698
+ "learning_rate": 0.0001124004550625711,
699
+ "loss": 0.5009,
700
+ "mean_token_accuracy": 0.8934224143624305,
701
+ "num_tokens": 362020.0,
702
+ "step": 385
703
+ },
704
+ {
705
+ "epoch": 1.3282247765006385,
706
+ "grad_norm": 0.6634964942932129,
707
+ "learning_rate": 0.00011126279863481229,
708
+ "loss": 0.5414,
709
+ "mean_token_accuracy": 0.8910330131649971,
710
+ "num_tokens": 366728.0,
711
+ "step": 390
712
+ },
713
+ {
714
+ "epoch": 1.3452532992762878,
715
+ "grad_norm": 0.7004157304763794,
716
+ "learning_rate": 0.00011012514220705347,
717
+ "loss": 0.4922,
718
+ "mean_token_accuracy": 0.8992783546447753,
719
+ "num_tokens": 371381.0,
720
+ "step": 395
721
+ },
722
+ {
723
+ "epoch": 1.362281822051937,
724
+ "grad_norm": 0.6225594282150269,
725
+ "learning_rate": 0.00010898748577929466,
726
+ "loss": 0.5084,
727
+ "mean_token_accuracy": 0.8956901535391808,
728
+ "num_tokens": 376043.0,
729
+ "step": 400
730
+ },
731
+ {
732
+ "epoch": 1.3793103448275863,
733
+ "grad_norm": 0.8019647598266602,
734
+ "learning_rate": 0.00010784982935153584,
735
+ "loss": 0.5303,
736
+ "mean_token_accuracy": 0.8940754950046539,
737
+ "num_tokens": 380714.0,
738
+ "step": 405
739
+ },
740
+ {
741
+ "epoch": 1.3963388676032356,
742
+ "grad_norm": 0.8314201831817627,
743
+ "learning_rate": 0.00010671217292377703,
744
+ "loss": 0.5249,
745
+ "mean_token_accuracy": 0.8924115225672722,
746
+ "num_tokens": 385498.0,
747
+ "step": 410
748
+ },
749
+ {
750
+ "epoch": 1.4133673903788846,
751
+ "grad_norm": 0.6691393256187439,
752
+ "learning_rate": 0.00010557451649601821,
753
+ "loss": 0.4817,
754
+ "mean_token_accuracy": 0.89882483035326,
755
+ "num_tokens": 390179.0,
756
+ "step": 415
757
+ },
758
+ {
759
+ "epoch": 1.4303959131545338,
760
+ "grad_norm": 0.8554338216781616,
761
+ "learning_rate": 0.00010443686006825938,
762
+ "loss": 0.5191,
763
+ "mean_token_accuracy": 0.8876234069466591,
764
+ "num_tokens": 394930.0,
765
+ "step": 420
766
+ },
767
+ {
768
+ "epoch": 1.447424435930183,
769
+ "grad_norm": 0.696018636226654,
770
+ "learning_rate": 0.00010329920364050057,
771
+ "loss": 0.5386,
772
+ "mean_token_accuracy": 0.891503955423832,
773
+ "num_tokens": 399685.0,
774
+ "step": 425
775
+ },
776
+ {
777
+ "epoch": 1.4644529587058321,
778
+ "grad_norm": 0.7389529943466187,
779
+ "learning_rate": 0.00010216154721274175,
780
+ "loss": 0.4949,
781
+ "mean_token_accuracy": 0.9004919424653053,
782
+ "num_tokens": 404300.0,
783
+ "step": 430
784
+ },
785
+ {
786
+ "epoch": 1.4814814814814814,
787
+ "grad_norm": 1.0227491855621338,
788
+ "learning_rate": 0.00010102389078498294,
789
+ "loss": 0.54,
790
+ "mean_token_accuracy": 0.8893611416220665,
791
+ "num_tokens": 409079.0,
792
+ "step": 435
793
+ },
794
+ {
795
+ "epoch": 1.4985100042571307,
796
+ "grad_norm": 0.6526888012886047,
797
+ "learning_rate": 9.988623435722412e-05,
798
+ "loss": 0.4917,
799
+ "mean_token_accuracy": 0.8958082437515259,
800
+ "num_tokens": 413758.0,
801
+ "step": 440
802
+ },
803
+ {
804
+ "epoch": 1.51553852703278,
805
+ "grad_norm": 0.5875766277313232,
806
+ "learning_rate": 9.874857792946531e-05,
807
+ "loss": 0.4991,
808
+ "mean_token_accuracy": 0.8971148490905761,
809
+ "num_tokens": 418502.0,
810
+ "step": 445
811
+ },
812
+ {
813
+ "epoch": 1.5325670498084292,
814
+ "grad_norm": 0.6892980337142944,
815
+ "learning_rate": 9.761092150170649e-05,
816
+ "loss": 0.4551,
817
+ "mean_token_accuracy": 0.9068983420729637,
818
+ "num_tokens": 423099.0,
819
+ "step": 450
820
+ },
821
+ {
822
+ "epoch": 1.5495955725840784,
823
+ "grad_norm": 0.6264586448669434,
824
+ "learning_rate": 9.647326507394768e-05,
825
+ "loss": 0.468,
826
+ "mean_token_accuracy": 0.9043048679828644,
827
+ "num_tokens": 427701.0,
828
+ "step": 455
829
+ },
830
+ {
831
+ "epoch": 1.5666240953597277,
832
+ "grad_norm": 0.5398015379905701,
833
+ "learning_rate": 9.533560864618886e-05,
834
+ "loss": 0.4877,
835
+ "mean_token_accuracy": 0.8986729174852371,
836
+ "num_tokens": 432430.0,
837
+ "step": 460
838
+ },
839
+ {
840
+ "epoch": 1.5836526181353767,
841
+ "grad_norm": 0.827769935131073,
842
+ "learning_rate": 9.419795221843003e-05,
843
+ "loss": 0.4951,
844
+ "mean_token_accuracy": 0.9012611672282219,
845
+ "num_tokens": 437078.0,
846
+ "step": 465
847
+ },
848
+ {
849
+ "epoch": 1.600681140911026,
850
+ "grad_norm": 0.6888080835342407,
851
+ "learning_rate": 9.306029579067122e-05,
852
+ "loss": 0.5108,
853
+ "mean_token_accuracy": 0.8976602256298065,
854
+ "num_tokens": 441734.0,
855
+ "step": 470
856
+ },
857
+ {
858
+ "epoch": 1.617709663686675,
859
+ "grad_norm": 0.837681233882904,
860
+ "learning_rate": 9.19226393629124e-05,
861
+ "loss": 0.5377,
862
+ "mean_token_accuracy": 0.8850761532783509,
863
+ "num_tokens": 446637.0,
864
+ "step": 475
865
+ },
866
+ {
867
+ "epoch": 1.6347381864623243,
868
+ "grad_norm": 0.7211363315582275,
869
+ "learning_rate": 9.078498293515359e-05,
870
+ "loss": 0.5001,
871
+ "mean_token_accuracy": 0.898733913898468,
872
+ "num_tokens": 451301.0,
873
+ "step": 480
874
+ },
875
+ {
876
+ "epoch": 1.6517667092379735,
877
+ "grad_norm": 0.6663438081741333,
878
+ "learning_rate": 8.964732650739477e-05,
879
+ "loss": 0.5144,
880
+ "mean_token_accuracy": 0.8976200923323632,
881
+ "num_tokens": 455965.0,
882
+ "step": 485
883
+ },
884
+ {
885
+ "epoch": 1.6687952320136228,
886
+ "grad_norm": 0.8935639262199402,
887
+ "learning_rate": 8.850967007963596e-05,
888
+ "loss": 0.5331,
889
+ "mean_token_accuracy": 0.8960411131381989,
890
+ "num_tokens": 460716.0,
891
+ "step": 490
892
+ },
893
+ {
894
+ "epoch": 1.685823754789272,
895
+ "grad_norm": 0.7235546708106995,
896
+ "learning_rate": 8.737201365187714e-05,
897
+ "loss": 0.4831,
898
+ "mean_token_accuracy": 0.8972082689404488,
899
+ "num_tokens": 465370.0,
900
+ "step": 495
901
+ },
902
+ {
903
+ "epoch": 1.7028522775649213,
904
+ "grad_norm": 0.774000346660614,
905
+ "learning_rate": 8.623435722411833e-05,
906
+ "loss": 0.5186,
907
+ "mean_token_accuracy": 0.8950631290674209,
908
+ "num_tokens": 470043.0,
909
+ "step": 500
910
+ },
911
+ {
912
+ "epoch": 1.7198808003405706,
913
+ "grad_norm": 0.5213722586631775,
914
+ "learning_rate": 8.509670079635951e-05,
915
+ "loss": 0.4567,
916
+ "mean_token_accuracy": 0.9016156733036041,
917
+ "num_tokens": 474573.0,
918
+ "step": 505
919
+ },
920
+ {
921
+ "epoch": 1.7369093231162198,
922
+ "grad_norm": 0.7278684377670288,
923
+ "learning_rate": 8.395904436860069e-05,
924
+ "loss": 0.5545,
925
+ "mean_token_accuracy": 0.8925162181258202,
926
+ "num_tokens": 479305.0,
927
+ "step": 510
928
+ },
929
+ {
930
+ "epoch": 1.7539378458918689,
931
+ "grad_norm": 0.7252481579780579,
932
+ "learning_rate": 8.282138794084187e-05,
933
+ "loss": 0.496,
934
+ "mean_token_accuracy": 0.8953201442956924,
935
+ "num_tokens": 484033.0,
936
+ "step": 515
937
+ },
938
+ {
939
+ "epoch": 1.770966368667518,
940
+ "grad_norm": 0.727513313293457,
941
+ "learning_rate": 8.168373151308306e-05,
942
+ "loss": 0.5033,
943
+ "mean_token_accuracy": 0.8998701125383377,
944
+ "num_tokens": 488727.0,
945
+ "step": 520
946
+ },
947
+ {
948
+ "epoch": 1.7879948914431671,
949
+ "grad_norm": 0.5375337600708008,
950
+ "learning_rate": 8.054607508532424e-05,
951
+ "loss": 0.4903,
952
+ "mean_token_accuracy": 0.8960629358887673,
953
+ "num_tokens": 493411.0,
954
+ "step": 525
955
+ },
956
+ {
957
+ "epoch": 1.8050234142188164,
958
+ "grad_norm": 0.5851954221725464,
959
+ "learning_rate": 7.940841865756543e-05,
960
+ "loss": 0.5139,
961
+ "mean_token_accuracy": 0.8972602248191833,
962
+ "num_tokens": 498098.0,
963
+ "step": 530
964
+ },
965
+ {
966
+ "epoch": 1.8220519369944657,
967
+ "grad_norm": 0.6942209005355835,
968
+ "learning_rate": 7.827076222980661e-05,
969
+ "loss": 0.4728,
970
+ "mean_token_accuracy": 0.9009919315576553,
971
+ "num_tokens": 502717.0,
972
+ "step": 535
973
+ },
974
+ {
975
+ "epoch": 1.839080459770115,
976
+ "grad_norm": 0.9342221021652222,
977
+ "learning_rate": 7.71331058020478e-05,
978
+ "loss": 0.5283,
979
+ "mean_token_accuracy": 0.8924958631396294,
980
+ "num_tokens": 507462.0,
981
+ "step": 540
982
+ },
983
+ {
984
+ "epoch": 1.8561089825457642,
985
+ "grad_norm": 0.7415278553962708,
986
+ "learning_rate": 7.599544937428897e-05,
987
+ "loss": 0.5394,
988
+ "mean_token_accuracy": 0.8913042590022087,
989
+ "num_tokens": 512202.0,
990
+ "step": 545
991
+ },
992
+ {
993
+ "epoch": 1.8731375053214134,
994
+ "grad_norm": 0.7223448157310486,
995
+ "learning_rate": 7.485779294653015e-05,
996
+ "loss": 0.5473,
997
+ "mean_token_accuracy": 0.8873603999614715,
998
+ "num_tokens": 517047.0,
999
+ "step": 550
1000
+ },
1001
+ {
1002
+ "epoch": 1.8901660280970627,
1003
+ "grad_norm": 0.6324387192726135,
1004
+ "learning_rate": 7.372013651877134e-05,
1005
+ "loss": 0.4986,
1006
+ "mean_token_accuracy": 0.9018153563141823,
1007
+ "num_tokens": 521653.0,
1008
+ "step": 555
1009
+ },
1010
+ {
1011
+ "epoch": 1.907194550872712,
1012
+ "grad_norm": 0.6177689433097839,
1013
+ "learning_rate": 7.258248009101252e-05,
1014
+ "loss": 0.5242,
1015
+ "mean_token_accuracy": 0.8907949879765511,
1016
+ "num_tokens": 526387.0,
1017
+ "step": 560
1018
+ },
1019
+ {
1020
+ "epoch": 1.924223073648361,
1021
+ "grad_norm": 0.6327561140060425,
1022
+ "learning_rate": 7.14448236632537e-05,
1023
+ "loss": 0.4725,
1024
+ "mean_token_accuracy": 0.9006670027971267,
1025
+ "num_tokens": 531113.0,
1026
+ "step": 565
1027
+ },
1028
+ {
1029
+ "epoch": 1.9412515964240102,
1030
+ "grad_norm": 0.6829894781112671,
1031
+ "learning_rate": 7.030716723549489e-05,
1032
+ "loss": 0.5255,
1033
+ "mean_token_accuracy": 0.8897917374968529,
1034
+ "num_tokens": 535963.0,
1035
+ "step": 570
1036
+ },
1037
+ {
1038
+ "epoch": 1.9582801191996593,
1039
+ "grad_norm": 0.7764301896095276,
1040
+ "learning_rate": 6.916951080773608e-05,
1041
+ "loss": 0.5636,
1042
+ "mean_token_accuracy": 0.8877105817198754,
1043
+ "num_tokens": 540801.0,
1044
+ "step": 575
1045
+ },
1046
+ {
1047
+ "epoch": 1.9753086419753085,
1048
+ "grad_norm": 0.7201740741729736,
1049
+ "learning_rate": 6.803185437997726e-05,
1050
+ "loss": 0.5279,
1051
+ "mean_token_accuracy": 0.8954470381140709,
1052
+ "num_tokens": 545507.0,
1053
+ "step": 580
1054
+ },
1055
+ {
1056
+ "epoch": 1.9923371647509578,
1057
+ "grad_norm": 0.6038010716438293,
1058
+ "learning_rate": 6.689419795221843e-05,
1059
+ "loss": 0.505,
1060
+ "mean_token_accuracy": 0.8970827981829643,
1061
+ "num_tokens": 550257.0,
1062
+ "step": 585
1063
+ },
1064
+ {
1065
+ "epoch": 2.009365687526607,
1066
+ "grad_norm": 0.5724640488624573,
1067
+ "learning_rate": 6.575654152445962e-05,
1068
+ "loss": 0.5361,
1069
+ "mean_token_accuracy": 0.9015150561928749,
1070
+ "num_tokens": 554990.0,
1071
+ "step": 590
1072
+ },
1073
+ {
1074
+ "epoch": 2.0263942103022563,
1075
+ "grad_norm": 0.5974262952804565,
1076
+ "learning_rate": 6.46188850967008e-05,
1077
+ "loss": 0.3674,
1078
+ "mean_token_accuracy": 0.922430993616581,
1079
+ "num_tokens": 559672.0,
1080
+ "step": 595
1081
+ },
1082
+ {
1083
+ "epoch": 2.0434227330779056,
1084
+ "grad_norm": 0.6744574904441833,
1085
+ "learning_rate": 6.348122866894199e-05,
1086
+ "loss": 0.3751,
1087
+ "mean_token_accuracy": 0.9247258752584457,
1088
+ "num_tokens": 564411.0,
1089
+ "step": 600
1090
+ }
1091
+ ],
1092
+ "logging_steps": 5,
1093
+ "max_steps": 879,
1094
+ "num_input_tokens_seen": 0,
1095
+ "num_train_epochs": 3,
1096
+ "save_steps": 200,
1097
+ "stateful_callbacks": {
1098
+ "TrainerControl": {
1099
+ "args": {
1100
+ "should_epoch_stop": false,
1101
+ "should_evaluate": false,
1102
+ "should_log": false,
1103
+ "should_save": true,
1104
+ "should_training_stop": false
1105
+ },
1106
+ "attributes": {}
1107
+ }
1108
+ },
1109
+ "total_flos": 2.555721091318579e+16,
1110
+ "train_batch_size": 1,
1111
+ "trial_name": null,
1112
+ "trial_params": null
1113
+ }
checkpoint-600/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc4e07dc6df6129e6d2045027becfa7300f4a8ae9e98a02f1c9d1066e93703ce
3
+ size 5624
checkpoint-800/README.md ADDED
@@ -0,0 +1,209 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: NousResearch/Hermes-3-Llama-3.1-8B
3
+ library_name: peft
4
+ pipeline_tag: text-generation
5
+ tags:
6
+ - base_model:adapter:NousResearch/Hermes-3-Llama-3.1-8B
7
+ - lora
8
+ - sft
9
+ - transformers
10
+ - trl
11
+ ---
12
+
13
+ # Model Card for Model ID
14
+
15
+ <!-- Provide a quick summary of what the model is/does. -->
16
+
17
+
18
+
19
+ ## Model Details
20
+
21
+ ### Model Description
22
+
23
+ <!-- Provide a longer summary of what this model is. -->
24
+
25
+
26
+
27
+ - **Developed by:** [More Information Needed]
28
+ - **Funded by [optional]:** [More Information Needed]
29
+ - **Shared by [optional]:** [More Information Needed]
30
+ - **Model type:** [More Information Needed]
31
+ - **Language(s) (NLP):** [More Information Needed]
32
+ - **License:** [More Information Needed]
33
+ - **Finetuned from model [optional]:** [More Information Needed]
34
+
35
+ ### Model Sources [optional]
36
+
37
+ <!-- Provide the basic links for the model. -->
38
+
39
+ - **Repository:** [More Information Needed]
40
+ - **Paper [optional]:** [More Information Needed]
41
+ - **Demo [optional]:** [More Information Needed]
42
+
43
+ ## Uses
44
+
45
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
46
+
47
+ ### Direct Use
48
+
49
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
50
+
51
+ [More Information Needed]
52
+
53
+ ### Downstream Use [optional]
54
+
55
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
56
+
57
+ [More Information Needed]
58
+
59
+ ### Out-of-Scope Use
60
+
61
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
62
+
63
+ [More Information Needed]
64
+
65
+ ## Bias, Risks, and Limitations
66
+
67
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
68
+
69
+ [More Information Needed]
70
+
71
+ ### Recommendations
72
+
73
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
74
+
75
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
76
+
77
+ ## How to Get Started with the Model
78
+
79
+ Use the code below to get started with the model.
80
+
81
+ [More Information Needed]
82
+
83
+ ## Training Details
84
+
85
+ ### Training Data
86
+
87
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
88
+
89
+ [More Information Needed]
90
+
91
+ ### Training Procedure
92
+
93
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
94
+
95
+ #### Preprocessing [optional]
96
+
97
+ [More Information Needed]
98
+
99
+
100
+ #### Training Hyperparameters
101
+
102
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
103
+
104
+ #### Speeds, Sizes, Times [optional]
105
+
106
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
107
+
108
+ [More Information Needed]
109
+
110
+ ## Evaluation
111
+
112
+ <!-- This section describes the evaluation protocols and provides the results. -->
113
+
114
+ ### Testing Data, Factors & Metrics
115
+
116
+ #### Testing Data
117
+
118
+ <!-- This should link to a Dataset Card if possible. -->
119
+
120
+ [More Information Needed]
121
+
122
+ #### Factors
123
+
124
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
125
+
126
+ [More Information Needed]
127
+
128
+ #### Metrics
129
+
130
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
131
+
132
+ [More Information Needed]
133
+
134
+ ### Results
135
+
136
+ [More Information Needed]
137
+
138
+ #### Summary
139
+
140
+
141
+
142
+ ## Model Examination [optional]
143
+
144
+ <!-- Relevant interpretability work for the model goes here -->
145
+
146
+ [More Information Needed]
147
+
148
+ ## Environmental Impact
149
+
150
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
151
+
152
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
153
+
154
+ - **Hardware Type:** [More Information Needed]
155
+ - **Hours used:** [More Information Needed]
156
+ - **Cloud Provider:** [More Information Needed]
157
+ - **Compute Region:** [More Information Needed]
158
+ - **Carbon Emitted:** [More Information Needed]
159
+
160
+ ## Technical Specifications [optional]
161
+
162
+ ### Model Architecture and Objective
163
+
164
+ [More Information Needed]
165
+
166
+ ### Compute Infrastructure
167
+
168
+ [More Information Needed]
169
+
170
+ #### Hardware
171
+
172
+ [More Information Needed]
173
+
174
+ #### Software
175
+
176
+ [More Information Needed]
177
+
178
+ ## Citation [optional]
179
+
180
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
181
+
182
+ **BibTeX:**
183
+
184
+ [More Information Needed]
185
+
186
+ **APA:**
187
+
188
+ [More Information Needed]
189
+
190
+ ## Glossary [optional]
191
+
192
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
193
+
194
+ [More Information Needed]
195
+
196
+ ## More Information [optional]
197
+
198
+ [More Information Needed]
199
+
200
+ ## Model Card Authors [optional]
201
+
202
+ [More Information Needed]
203
+
204
+ ## Model Card Contact
205
+
206
+ [More Information Needed]
207
+ ### Framework versions
208
+
209
+ - PEFT 0.20.0
checkpoint-800/adapter_config.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alora_invocation_tokens": null,
3
+ "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": null,
6
+ "base_model_name_or_path": "NousResearch/Hermes-3-Llama-3.1-8B",
7
+ "bias": "none",
8
+ "corda_config": null,
9
+ "ensure_weight_tying": false,
10
+ "eva_config": null,
11
+ "exclude_modules": null,
12
+ "fan_in_fan_out": false,
13
+ "inference_mode": true,
14
+ "init_lora_weights": true,
15
+ "layer_replication": null,
16
+ "layers_pattern": null,
17
+ "layers_to_transform": null,
18
+ "loftq_config": {},
19
+ "lora_alpha": 32,
20
+ "lora_bias": false,
21
+ "lora_dropout": 0.05,
22
+ "lora_ga_config": null,
23
+ "megatron_config": null,
24
+ "megatron_core": "megatron.core",
25
+ "modules_to_save": null,
26
+ "monteclora_config": null,
27
+ "peft_type": "LORA",
28
+ "peft_version": "0.20.0",
29
+ "qalora_group_size": 16,
30
+ "r": 16,
31
+ "rank_pattern": {},
32
+ "revision": null,
33
+ "target_modules": [
34
+ "v_proj",
35
+ "q_proj",
36
+ "k_proj",
37
+ "down_proj",
38
+ "up_proj",
39
+ "gate_proj",
40
+ "o_proj"
41
+ ],
42
+ "target_parameters": null,
43
+ "task_type": "CAUSAL_LM",
44
+ "trainable_token_indices": null,
45
+ "use_bdlora": null,
46
+ "use_dora": false,
47
+ "use_qalora": false,
48
+ "use_rslora": false,
49
+ "velora_config": null
50
+ }
checkpoint-800/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:604e0297d18f2a6234febc7f5a1bd753c0ad23a1a5b02aefc9ba06deb502ac9d
3
+ size 167832240
checkpoint-800/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2091dee88dd86d212cf9d3247ab597eddbf81bd87cd1514b8e09eb6c9e4e04d
3
+ size 85728276
checkpoint-800/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99051acd34ec5b53d2d7f281dab4b9b826e579cc685b1c8c008e4b30c106485f
3
+ size 14244
checkpoint-800/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4225c4e9f1ab7f7ed353e670836f9ef1773c433469b40387b8cbe0244cf93748
3
+ size 1064
checkpoint-800/special_tokens_map.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|im_end|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|im_end|>"
17
+ }
checkpoint-800/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14b5e679cb69af62e14c3b98d346177bd4137d882a44f87dec9efec982b01a05
3
+ size 17209403
checkpoint-800/tokenizer_config.json ADDED
@@ -0,0 +1,2072 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<tool_call>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": false
26
+ },
27
+ "128003": {
28
+ "content": "<tool_response>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": false
34
+ },
35
+ "128004": {
36
+ "content": "<|finetune_right_pad_id|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_2|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128006": {
52
+ "content": "<|start_header_id|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "128007": {
60
+ "content": "<|end_header_id|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "128008": {
68
+ "content": "<|eom_id|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "128009": {
76
+ "content": "<|eot_id|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "128010": {
84
+ "content": "<|python_tag|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<tools>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": false
98
+ },
99
+ "128012": {
100
+ "content": "</tools>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": false
106
+ },
107
+ "128013": {
108
+ "content": "</tool_call>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": false
114
+ },
115
+ "128014": {
116
+ "content": "</tool_response>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": false
122
+ },
123
+ "128015": {
124
+ "content": "<schema>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": false
130
+ },
131
+ "128016": {
132
+ "content": "</schema>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": false
138
+ },
139
+ "128017": {
140
+ "content": "<scratch_pad>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": false
146
+ },
147
+ "128018": {
148
+ "content": "</scratch_pad>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": false
154
+ },
155
+ "128019": {
156
+ "content": "<SCRATCHPAD>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": false
162
+ },
163
+ "128020": {
164
+ "content": "</SCRATCHPAD>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": false
170
+ },
171
+ "128021": {
172
+ "content": "<REASONING>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": false
178
+ },
179
+ "128022": {
180
+ "content": "</REASONING>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": false
186
+ },
187
+ "128023": {
188
+ "content": "<INNER_MONOLOGUE>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": false
194
+ },
195
+ "128024": {
196
+ "content": "</INNER_MONOLOGUE>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": false
202
+ },
203
+ "128025": {
204
+ "content": "<PLAN>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": false
210
+ },
211
+ "128026": {
212
+ "content": "</PLAN>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": false
218
+ },
219
+ "128027": {
220
+ "content": "<EXECUTION>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": false
226
+ },
227
+ "128028": {
228
+ "content": "</EXECUTION>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": false
234
+ },
235
+ "128029": {
236
+ "content": "<REFLECTION>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": false
242
+ },
243
+ "128030": {
244
+ "content": "</REFLECTION>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": false
250
+ },
251
+ "128031": {
252
+ "content": "<THINKING>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": false
258
+ },
259
+ "128032": {
260
+ "content": "</THINKING>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": false
266
+ },
267
+ "128033": {
268
+ "content": "<SOLUTION>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": false
274
+ },
275
+ "128034": {
276
+ "content": "</SOLUTION>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": false
282
+ },
283
+ "128035": {
284
+ "content": "<EXPLANATION>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": false
290
+ },
291
+ "128036": {
292
+ "content": "</EXPLANATION>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": false
298
+ },
299
+ "128037": {
300
+ "content": "<UNIT_TEST>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": false
306
+ },
307
+ "128038": {
308
+ "content": "</UNIT_TEST>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": false
314
+ },
315
+ "128039": {
316
+ "content": "<|im_start|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": false
322
+ },
323
+ "128040": {
324
+ "content": "<|im_end|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_33|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_34|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_35|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_36|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_37|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_38|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_39|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_40|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_41|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_42|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_43|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_44|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_45|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_46|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_47|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_48|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_49|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_50|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_51|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_52|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_53|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_54|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_55|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_56|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_57|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_58|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_59|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_60|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_61|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_62|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_63|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_64|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_65|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_66|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_67|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_68|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_69|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_70|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_71|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_72|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_73|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_74|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_75|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_76|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_77|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_78|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_79|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_80|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_81|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_82|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_83|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_84|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_85|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_86|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_87|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_88|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_89|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_90|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_91|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_92|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_93|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_94|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_95|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_96|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_97|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_98|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_99|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_100|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_101|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_102|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_103|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_104|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_105|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_106|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_107|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_108|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_109|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_110|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_111|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_112|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_113|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_114|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_115|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_116|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_117|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_118|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_119|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_120|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_121|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_122|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_123|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_124|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_125|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_126|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_127|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_128|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_129|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_130|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_131|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_132|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_133|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_134|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_135|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_136|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_137|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_138|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_139|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_140|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_141|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_142|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_143|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_144|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_145|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_146|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_147|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_148|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_149|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_150|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_151|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_152|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_153|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_154|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_155|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_156|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_157|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_158|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_159|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_160|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_161|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_162|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_163|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_164|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_165|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_166|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_167|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_168|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_169|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_170|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_171|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_172|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_173|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_174|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_175|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_176|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_177|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_178|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_179|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_180|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_181|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_182|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_183|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_184|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_185|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_186|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_187|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_188|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_189|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_190|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_191|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_192|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_193|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_194|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_195|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_196|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_197|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_198|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_199|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_200|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_201|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_202|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_203|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_204|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_205|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_206|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_207|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_208|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_209|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_210|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_211|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_212|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_213|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_214|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_215|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_216|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_217|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_218|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_219|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_220|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_221|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_222|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_223|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_224|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_225|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_226|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_227|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_228|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_229|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_230|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_231|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_232|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_233|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_234|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_235|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_236|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_237|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_238|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_239|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_240|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_241|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_242|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_243|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_244|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_245|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_246|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_247|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ }
2051
+ },
2052
+ "bos_token": "<|begin_of_text|>",
2053
+ "chat_template": [
2054
+ {
2055
+ "name": "default",
2056
+ "template": "{{bos_token}}{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}"
2057
+ },
2058
+ {
2059
+ "name": "tool_use",
2060
+ "template": "{%- macro json_to_python_type(json_spec) %}\n{%- set basic_type_map = {\n \"string\": \"str\",\n \"number\": \"float\",\n \"integer\": \"int\",\n \"boolean\": \"bool\"\n} %}\n\n{%- if basic_type_map[json_spec.type] is defined %}\n {{- basic_type_map[json_spec.type] }}\n{%- elif json_spec.type == \"array\" %}\n {{- \"list[\" + json_to_python_type(json_spec|items) + \"]\"}}\n{%- elif json_spec.type == \"object\" %}\n {%- if json_spec.additionalProperties is defined %}\n {{- \"dict[str, \" + json_to_python_type(json_spec.additionalProperties) + ']'}}\n {%- else %}\n {{- \"dict\" }}\n {%- endif %}\n{%- elif json_spec.type is iterable %}\n {{- \"Union[\" }}\n {%- for t in json_spec.type %}\n {{- json_to_python_type({\"type\": t}) }}\n {%- if not loop.last %}\n {{- \",\" }} \n {%- endif %}\n {%- endfor %}\n {{- \"]\" }}\n{%- else %}\n {{- \"Any\" }}\n{%- endif %}\n{%- endmacro %}\n\n\n{{- bos_token }}\n{{- '<|im_start|>system\n' }}\n{{- \"You are a function calling AI model. You are provided with function signatures within <tools></tools> XML tags. You may call one or more functions to assist with the user query. Don't make assumptions about what values to plug into functions. Here are the available tools: <tools> \" }}\n{%- for tool in tools %}\n {%- if tool.function is defined %}\n {%- set tool = tool.function %}\n {%- endif %}\n {{- '{\"type\": \"function\", \"function\": ' }}\n {{- '{\"name\": \"' + tool.name + '\", ' }}\n {{- '\"description\": \"' + tool.name + '(' }}\n {%- for param_name, param_fields in tool.parameters.properties|items %}\n {{- param_name + \": \" + json_to_python_type(param_fields) }}\n {%- if not loop.last %}\n {{- \", \" }}\n {%- endif %}\n {%- endfor %}\n {{- \")\" }}\n {%- if tool.return is defined %}\n {{- \" -> \" + json_to_python_type(tool.return) }}\n {%- endif %}\n {{- \" - \" + tool.description + \"\n\n\" }}\n {%- for param_name, param_fields in tool.parameters.properties|items %}\n {%- if loop.first %}\n {{- \" Args:\n\" }}\n {%- endif %}\n {{- \" \" + param_name + \"(\" + json_to_python_type(param_fields) + \"): \" + param_fields.description|trim }}\n {%- endfor %}\n {%- if tool.return is defined and tool.return.description is defined %}\n {{- \"\n Returns:\n \" + tool.return.description }}\n {%- endif %}\n {{- '\"' }}\n {{- ', \"parameters\": ' }}\n {%- if tool.parameters.properties | length == 0 %}\n {{- \"{}\" }}\n {%- else %}\n {{- tool.parameters|tojson }}\n {%- endif %}\n {{- \"}\" }}\n {%- if not loop.last %}\n {{- \"\n\" }}\n {%- endif %}\n{%- endfor %}\n{{- \" </tools>\" }}\n{{- 'Use the following pydantic model json schema for each tool call you will make: {\"properties\": {\"name\": {\"title\": \"Name\", \"type\": \"string\"}, \"arguments\": {\"title\": \"Arguments\", \"type\": \"object\"}}, \"required\": [\"name\", \"arguments\"], \"title\": \"FunctionCall\", \"type\": \"object\"}}\n' }}\n{{- \"For each function call return a json object with function name and arguments within <tool_call></tool_call> XML tags as follows:\n\" }}\n{{- \"<tool_call>\n\" }}\n{{- '{\"name\": <function-name>, \"arguments\": <args-dict>}\n' }}\n{{- '</tool_call><|im_end|>\n' }}\n{%- for message in messages %}\n {%- if message.role == \"user\" or message.role == \"system\" or (message.role == \"assistant\" and message.tool_calls is not defined) %}\n {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- for tool_call in message.tool_calls %}\n {{- '\n<tool_call>\n' }} {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '{' }}\n {{- '\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\"' }}\n {{- ', '}}\n {%- if tool_call.arguments is defined %}\n {{- '\"arguments\": ' }}\n {%- if tool_call.arguments is string %}\n {{- tool_call.arguments }}\n {%- else %}\n {{- tool_call.arguments|tojson }}\n {%- endif %}\n {%- endif %}\n {{- '}' }}\n {{- '\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.previtem and loop.previtem.role != \"tool\" %}\n {{- '<|im_start|>tool\n' }}\n {%- endif %}\n {{- '<tool_response>\n' }}\n {{- message.content }}\n {%- if not loop.last %}\n {{- '\n</tool_response>\n' }}\n {%- else %}\n {{- '\n</tool_response>' }}\n {%- endif %}\n {%- if not loop.last and loop.nextitem.role != \"tool\" %}\n {{- '<|im_end|>' }}\n {%- elif loop.last %}\n {{- '<|im_end|>' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\n' }}\n{%- endif %}\n"
2061
+ }
2062
+ ],
2063
+ "clean_up_tokenization_spaces": true,
2064
+ "eos_token": "<|im_end|>",
2065
+ "model_input_names": [
2066
+ "input_ids",
2067
+ "attention_mask"
2068
+ ],
2069
+ "model_max_length": 131072,
2070
+ "pad_token": "<|im_end|>",
2071
+ "tokenizer_class": "PreTrainedTokenizerFast"
2072
+ }
checkpoint-800/trainer_state.json ADDED
@@ -0,0 +1,1473 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.724563644103874,
5
+ "eval_steps": 500,
6
+ "global_step": 800,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.017028522775649212,
13
+ "grad_norm": 6.522716999053955,
14
+ "learning_rate": 0.0001988623435722412,
15
+ "loss": 2.7211,
16
+ "mean_token_accuracy": 0.5789041496813297,
17
+ "num_tokens": 4727.0,
18
+ "step": 5
19
+ },
20
+ {
21
+ "epoch": 0.034057045551298425,
22
+ "grad_norm": 1.0070050954818726,
23
+ "learning_rate": 0.00019772468714448238,
24
+ "loss": 0.9998,
25
+ "mean_token_accuracy": 0.8499793156981468,
26
+ "num_tokens": 9471.0,
27
+ "step": 10
28
+ },
29
+ {
30
+ "epoch": 0.05108556832694764,
31
+ "grad_norm": 0.7373425960540771,
32
+ "learning_rate": 0.00019658703071672356,
33
+ "loss": 0.8303,
34
+ "mean_token_accuracy": 0.8681916877627373,
35
+ "num_tokens": 14013.0,
36
+ "step": 15
37
+ },
38
+ {
39
+ "epoch": 0.06811409110259685,
40
+ "grad_norm": 0.8468236327171326,
41
+ "learning_rate": 0.00019544937428896475,
42
+ "loss": 0.8404,
43
+ "mean_token_accuracy": 0.8622620105743408,
44
+ "num_tokens": 18725.0,
45
+ "step": 20
46
+ },
47
+ {
48
+ "epoch": 0.08514261387824607,
49
+ "grad_norm": 0.8178804516792297,
50
+ "learning_rate": 0.00019431171786120593,
51
+ "loss": 0.9073,
52
+ "mean_token_accuracy": 0.8524447843432427,
53
+ "num_tokens": 23497.0,
54
+ "step": 25
55
+ },
56
+ {
57
+ "epoch": 0.10217113665389528,
58
+ "grad_norm": 0.890177309513092,
59
+ "learning_rate": 0.00019317406143344712,
60
+ "loss": 0.8029,
61
+ "mean_token_accuracy": 0.8642359614372254,
62
+ "num_tokens": 28192.0,
63
+ "step": 30
64
+ },
65
+ {
66
+ "epoch": 0.11919965942954448,
67
+ "grad_norm": 1.0545469522476196,
68
+ "learning_rate": 0.0001920364050056883,
69
+ "loss": 0.7458,
70
+ "mean_token_accuracy": 0.8732351213693619,
71
+ "num_tokens": 32805.0,
72
+ "step": 35
73
+ },
74
+ {
75
+ "epoch": 0.1362281822051937,
76
+ "grad_norm": 1.0384492874145508,
77
+ "learning_rate": 0.00019089874857792946,
78
+ "loss": 0.9235,
79
+ "mean_token_accuracy": 0.8408558666706085,
80
+ "num_tokens": 37714.0,
81
+ "step": 40
82
+ },
83
+ {
84
+ "epoch": 0.1532567049808429,
85
+ "grad_norm": 0.6860374808311462,
86
+ "learning_rate": 0.00018976109215017067,
87
+ "loss": 0.7623,
88
+ "mean_token_accuracy": 0.8656536340713501,
89
+ "num_tokens": 42429.0,
90
+ "step": 45
91
+ },
92
+ {
93
+ "epoch": 0.17028522775649213,
94
+ "grad_norm": 0.7284501791000366,
95
+ "learning_rate": 0.00018862343572241183,
96
+ "loss": 0.7588,
97
+ "mean_token_accuracy": 0.8688850715756417,
98
+ "num_tokens": 47099.0,
99
+ "step": 50
100
+ },
101
+ {
102
+ "epoch": 0.18731375053214133,
103
+ "grad_norm": 0.8899862170219421,
104
+ "learning_rate": 0.00018748577929465302,
105
+ "loss": 0.7065,
106
+ "mean_token_accuracy": 0.8717748820781708,
107
+ "num_tokens": 51795.0,
108
+ "step": 55
109
+ },
110
+ {
111
+ "epoch": 0.20434227330779056,
112
+ "grad_norm": 0.5350505709648132,
113
+ "learning_rate": 0.0001863481228668942,
114
+ "loss": 0.6696,
115
+ "mean_token_accuracy": 0.8851396456360817,
116
+ "num_tokens": 56369.0,
117
+ "step": 60
118
+ },
119
+ {
120
+ "epoch": 0.22137079608343976,
121
+ "grad_norm": 0.6087013483047485,
122
+ "learning_rate": 0.0001852104664391354,
123
+ "loss": 0.7204,
124
+ "mean_token_accuracy": 0.8682332798838616,
125
+ "num_tokens": 61018.0,
126
+ "step": 65
127
+ },
128
+ {
129
+ "epoch": 0.23839931885908897,
130
+ "grad_norm": 0.7879019379615784,
131
+ "learning_rate": 0.00018407281001137657,
132
+ "loss": 0.7692,
133
+ "mean_token_accuracy": 0.8653983056545258,
134
+ "num_tokens": 65741.0,
135
+ "step": 70
136
+ },
137
+ {
138
+ "epoch": 0.2554278416347382,
139
+ "grad_norm": 0.6546444296836853,
140
+ "learning_rate": 0.00018293515358361776,
141
+ "loss": 0.7119,
142
+ "mean_token_accuracy": 0.8726310178637504,
143
+ "num_tokens": 70425.0,
144
+ "step": 75
145
+ },
146
+ {
147
+ "epoch": 0.2724563644103874,
148
+ "grad_norm": 0.770902156829834,
149
+ "learning_rate": 0.00018179749715585894,
150
+ "loss": 0.7035,
151
+ "mean_token_accuracy": 0.8711811751127243,
152
+ "num_tokens": 75101.0,
153
+ "step": 80
154
+ },
155
+ {
156
+ "epoch": 0.2894848871860366,
157
+ "grad_norm": 0.8873187899589539,
158
+ "learning_rate": 0.00018065984072810013,
159
+ "loss": 0.7419,
160
+ "mean_token_accuracy": 0.8616803497076034,
161
+ "num_tokens": 79888.0,
162
+ "step": 85
163
+ },
164
+ {
165
+ "epoch": 0.3065134099616858,
166
+ "grad_norm": 0.7061370015144348,
167
+ "learning_rate": 0.0001795221843003413,
168
+ "loss": 0.66,
169
+ "mean_token_accuracy": 0.8744896531105042,
170
+ "num_tokens": 84562.0,
171
+ "step": 90
172
+ },
173
+ {
174
+ "epoch": 0.32354193273733506,
175
+ "grad_norm": 0.8232033252716064,
176
+ "learning_rate": 0.0001783845278725825,
177
+ "loss": 0.7403,
178
+ "mean_token_accuracy": 0.8659066379070282,
179
+ "num_tokens": 89238.0,
180
+ "step": 95
181
+ },
182
+ {
183
+ "epoch": 0.34057045551298426,
184
+ "grad_norm": 0.7313310503959656,
185
+ "learning_rate": 0.00017724687144482368,
186
+ "loss": 0.7157,
187
+ "mean_token_accuracy": 0.8661555901169777,
188
+ "num_tokens": 93987.0,
189
+ "step": 100
190
+ },
191
+ {
192
+ "epoch": 0.35759897828863346,
193
+ "grad_norm": 0.7119390964508057,
194
+ "learning_rate": 0.00017610921501706487,
195
+ "loss": 0.7016,
196
+ "mean_token_accuracy": 0.8678551658987999,
197
+ "num_tokens": 98722.0,
198
+ "step": 105
199
+ },
200
+ {
201
+ "epoch": 0.37462750106428266,
202
+ "grad_norm": 0.7126006484031677,
203
+ "learning_rate": 0.00017497155858930602,
204
+ "loss": 0.7009,
205
+ "mean_token_accuracy": 0.867291408777237,
206
+ "num_tokens": 103439.0,
207
+ "step": 110
208
+ },
209
+ {
210
+ "epoch": 0.39165602383993187,
211
+ "grad_norm": 0.6158230304718018,
212
+ "learning_rate": 0.00017383390216154724,
213
+ "loss": 0.7236,
214
+ "mean_token_accuracy": 0.8636128515005111,
215
+ "num_tokens": 108209.0,
216
+ "step": 115
217
+ },
218
+ {
219
+ "epoch": 0.4086845466155811,
220
+ "grad_norm": 0.6498322486877441,
221
+ "learning_rate": 0.0001726962457337884,
222
+ "loss": 0.6813,
223
+ "mean_token_accuracy": 0.8757071048021317,
224
+ "num_tokens": 112855.0,
225
+ "step": 120
226
+ },
227
+ {
228
+ "epoch": 0.4257130693912303,
229
+ "grad_norm": 0.6594287157058716,
230
+ "learning_rate": 0.0001715585893060296,
231
+ "loss": 0.7062,
232
+ "mean_token_accuracy": 0.8650311172008515,
233
+ "num_tokens": 117653.0,
234
+ "step": 125
235
+ },
236
+ {
237
+ "epoch": 0.4427415921668795,
238
+ "grad_norm": 0.7375237941741943,
239
+ "learning_rate": 0.00017042093287827076,
240
+ "loss": 0.6477,
241
+ "mean_token_accuracy": 0.8733970731496811,
242
+ "num_tokens": 122397.0,
243
+ "step": 130
244
+ },
245
+ {
246
+ "epoch": 0.45977011494252873,
247
+ "grad_norm": 0.5958442687988281,
248
+ "learning_rate": 0.00016928327645051198,
249
+ "loss": 0.691,
250
+ "mean_token_accuracy": 0.8681387722492218,
251
+ "num_tokens": 127136.0,
252
+ "step": 135
253
+ },
254
+ {
255
+ "epoch": 0.47679863771817793,
256
+ "grad_norm": 0.7407785654067993,
257
+ "learning_rate": 0.00016814562002275313,
258
+ "loss": 0.6477,
259
+ "mean_token_accuracy": 0.8752307429909706,
260
+ "num_tokens": 131833.0,
261
+ "step": 140
262
+ },
263
+ {
264
+ "epoch": 0.49382716049382713,
265
+ "grad_norm": 0.8190199732780457,
266
+ "learning_rate": 0.00016700796359499432,
267
+ "loss": 0.6608,
268
+ "mean_token_accuracy": 0.8762851104140281,
269
+ "num_tokens": 136441.0,
270
+ "step": 145
271
+ },
272
+ {
273
+ "epoch": 0.5108556832694764,
274
+ "grad_norm": 0.7571837306022644,
275
+ "learning_rate": 0.0001658703071672355,
276
+ "loss": 0.673,
277
+ "mean_token_accuracy": 0.8691665843129158,
278
+ "num_tokens": 141186.0,
279
+ "step": 150
280
+ },
281
+ {
282
+ "epoch": 0.5278842060451255,
283
+ "grad_norm": 0.6653426885604858,
284
+ "learning_rate": 0.0001647326507394767,
285
+ "loss": 0.7126,
286
+ "mean_token_accuracy": 0.8647830635309219,
287
+ "num_tokens": 145971.0,
288
+ "step": 155
289
+ },
290
+ {
291
+ "epoch": 0.5449127288207748,
292
+ "grad_norm": 0.7333567142486572,
293
+ "learning_rate": 0.00016359499431171787,
294
+ "loss": 0.6287,
295
+ "mean_token_accuracy": 0.878324082493782,
296
+ "num_tokens": 150669.0,
297
+ "step": 160
298
+ },
299
+ {
300
+ "epoch": 0.561941251596424,
301
+ "grad_norm": 0.8214460015296936,
302
+ "learning_rate": 0.00016245733788395906,
303
+ "loss": 0.6608,
304
+ "mean_token_accuracy": 0.8729922890663147,
305
+ "num_tokens": 155374.0,
306
+ "step": 165
307
+ },
308
+ {
309
+ "epoch": 0.5789697743720732,
310
+ "grad_norm": 0.6251844167709351,
311
+ "learning_rate": 0.00016131968145620024,
312
+ "loss": 0.6556,
313
+ "mean_token_accuracy": 0.8770609870553017,
314
+ "num_tokens": 160068.0,
315
+ "step": 170
316
+ },
317
+ {
318
+ "epoch": 0.5959982971477225,
319
+ "grad_norm": 0.804166853427887,
320
+ "learning_rate": 0.00016018202502844143,
321
+ "loss": 0.6366,
322
+ "mean_token_accuracy": 0.8760894432663917,
323
+ "num_tokens": 164696.0,
324
+ "step": 175
325
+ },
326
+ {
327
+ "epoch": 0.6130268199233716,
328
+ "grad_norm": 0.7013877034187317,
329
+ "learning_rate": 0.0001590443686006826,
330
+ "loss": 0.6328,
331
+ "mean_token_accuracy": 0.8779815405607223,
332
+ "num_tokens": 169356.0,
333
+ "step": 180
334
+ },
335
+ {
336
+ "epoch": 0.6300553426990209,
337
+ "grad_norm": 1.0623070001602173,
338
+ "learning_rate": 0.0001579067121729238,
339
+ "loss": 0.6734,
340
+ "mean_token_accuracy": 0.8710577815771103,
341
+ "num_tokens": 174041.0,
342
+ "step": 185
343
+ },
344
+ {
345
+ "epoch": 0.6470838654746701,
346
+ "grad_norm": 0.7858535647392273,
347
+ "learning_rate": 0.00015676905574516496,
348
+ "loss": 0.6775,
349
+ "mean_token_accuracy": 0.8692880481481552,
350
+ "num_tokens": 178858.0,
351
+ "step": 190
352
+ },
353
+ {
354
+ "epoch": 0.6641123882503193,
355
+ "grad_norm": 0.8943309187889099,
356
+ "learning_rate": 0.00015563139931740617,
357
+ "loss": 0.6874,
358
+ "mean_token_accuracy": 0.868885512650013,
359
+ "num_tokens": 183669.0,
360
+ "step": 195
361
+ },
362
+ {
363
+ "epoch": 0.6811409110259685,
364
+ "grad_norm": 0.5898745656013489,
365
+ "learning_rate": 0.00015449374288964733,
366
+ "loss": 0.6907,
367
+ "mean_token_accuracy": 0.8661940798163414,
368
+ "num_tokens": 188473.0,
369
+ "step": 200
370
+ },
371
+ {
372
+ "epoch": 0.6981694338016177,
373
+ "grad_norm": 0.6333857774734497,
374
+ "learning_rate": 0.00015335608646188854,
375
+ "loss": 0.6129,
376
+ "mean_token_accuracy": 0.8817986205220223,
377
+ "num_tokens": 193171.0,
378
+ "step": 205
379
+ },
380
+ {
381
+ "epoch": 0.7151979565772669,
382
+ "grad_norm": 0.5913947820663452,
383
+ "learning_rate": 0.0001522184300341297,
384
+ "loss": 0.5896,
385
+ "mean_token_accuracy": 0.8822762459516525,
386
+ "num_tokens": 197817.0,
387
+ "step": 210
388
+ },
389
+ {
390
+ "epoch": 0.7322264793529162,
391
+ "grad_norm": 0.6990242004394531,
392
+ "learning_rate": 0.00015108077360637088,
393
+ "loss": 0.6512,
394
+ "mean_token_accuracy": 0.8739180400967598,
395
+ "num_tokens": 202556.0,
396
+ "step": 215
397
+ },
398
+ {
399
+ "epoch": 0.7492550021285653,
400
+ "grad_norm": 0.6869048476219177,
401
+ "learning_rate": 0.00014994311717861207,
402
+ "loss": 0.7025,
403
+ "mean_token_accuracy": 0.8662877783179284,
404
+ "num_tokens": 207294.0,
405
+ "step": 220
406
+ },
407
+ {
408
+ "epoch": 0.7662835249042146,
409
+ "grad_norm": 0.5135166049003601,
410
+ "learning_rate": 0.00014880546075085325,
411
+ "loss": 0.6382,
412
+ "mean_token_accuracy": 0.8849207311868668,
413
+ "num_tokens": 211927.0,
414
+ "step": 225
415
+ },
416
+ {
417
+ "epoch": 0.7833120476798637,
418
+ "grad_norm": 0.6304216980934143,
419
+ "learning_rate": 0.00014766780432309444,
420
+ "loss": 0.6834,
421
+ "mean_token_accuracy": 0.8688049465417862,
422
+ "num_tokens": 216626.0,
423
+ "step": 230
424
+ },
425
+ {
426
+ "epoch": 0.800340570455513,
427
+ "grad_norm": 0.6879922151565552,
428
+ "learning_rate": 0.00014653014789533562,
429
+ "loss": 0.6902,
430
+ "mean_token_accuracy": 0.8655798360705376,
431
+ "num_tokens": 221432.0,
432
+ "step": 235
433
+ },
434
+ {
435
+ "epoch": 0.8173690932311622,
436
+ "grad_norm": 0.6433548331260681,
437
+ "learning_rate": 0.0001453924914675768,
438
+ "loss": 0.6129,
439
+ "mean_token_accuracy": 0.8795880794525146,
440
+ "num_tokens": 226022.0,
441
+ "step": 240
442
+ },
443
+ {
444
+ "epoch": 0.8343976160068114,
445
+ "grad_norm": 0.7876724600791931,
446
+ "learning_rate": 0.000144254835039818,
447
+ "loss": 0.6441,
448
+ "mean_token_accuracy": 0.8729524433612823,
449
+ "num_tokens": 230692.0,
450
+ "step": 245
451
+ },
452
+ {
453
+ "epoch": 0.8514261387824607,
454
+ "grad_norm": 0.6494749188423157,
455
+ "learning_rate": 0.00014311717861205915,
456
+ "loss": 0.7033,
457
+ "mean_token_accuracy": 0.8632469072937965,
458
+ "num_tokens": 235400.0,
459
+ "step": 250
460
+ },
461
+ {
462
+ "epoch": 0.8684546615581098,
463
+ "grad_norm": 0.6332300305366516,
464
+ "learning_rate": 0.00014197952218430036,
465
+ "loss": 0.5947,
466
+ "mean_token_accuracy": 0.8860528379678726,
467
+ "num_tokens": 239997.0,
468
+ "step": 255
469
+ },
470
+ {
471
+ "epoch": 0.885483184333759,
472
+ "grad_norm": 0.7144895195960999,
473
+ "learning_rate": 0.00014084186575654152,
474
+ "loss": 0.649,
475
+ "mean_token_accuracy": 0.8745664536952973,
476
+ "num_tokens": 244704.0,
477
+ "step": 260
478
+ },
479
+ {
480
+ "epoch": 0.9025117071094083,
481
+ "grad_norm": 0.5460124015808105,
482
+ "learning_rate": 0.00013970420932878273,
483
+ "loss": 0.6622,
484
+ "mean_token_accuracy": 0.8692788198590279,
485
+ "num_tokens": 249428.0,
486
+ "step": 265
487
+ },
488
+ {
489
+ "epoch": 0.9195402298850575,
490
+ "grad_norm": 0.65619295835495,
491
+ "learning_rate": 0.0001385665529010239,
492
+ "loss": 0.657,
493
+ "mean_token_accuracy": 0.8737826406955719,
494
+ "num_tokens": 254150.0,
495
+ "step": 270
496
+ },
497
+ {
498
+ "epoch": 0.9365687526607067,
499
+ "grad_norm": 0.8474870324134827,
500
+ "learning_rate": 0.0001374288964732651,
501
+ "loss": 0.6607,
502
+ "mean_token_accuracy": 0.8756056800484657,
503
+ "num_tokens": 258826.0,
504
+ "step": 275
505
+ },
506
+ {
507
+ "epoch": 0.9535972754363559,
508
+ "grad_norm": 0.6054229736328125,
509
+ "learning_rate": 0.00013629124004550626,
510
+ "loss": 0.6526,
511
+ "mean_token_accuracy": 0.8718441724777222,
512
+ "num_tokens": 263524.0,
513
+ "step": 280
514
+ },
515
+ {
516
+ "epoch": 0.9706257982120051,
517
+ "grad_norm": 0.6568702459335327,
518
+ "learning_rate": 0.00013515358361774744,
519
+ "loss": 0.6174,
520
+ "mean_token_accuracy": 0.881709736585617,
521
+ "num_tokens": 268179.0,
522
+ "step": 285
523
+ },
524
+ {
525
+ "epoch": 0.9876543209876543,
526
+ "grad_norm": 0.7518045902252197,
527
+ "learning_rate": 0.00013401592718998863,
528
+ "loss": 0.5896,
529
+ "mean_token_accuracy": 0.885109031200409,
530
+ "num_tokens": 272803.0,
531
+ "step": 290
532
+ },
533
+ {
534
+ "epoch": 1.0046828437633035,
535
+ "grad_norm": 0.5392197370529175,
536
+ "learning_rate": 0.00013287827076222981,
537
+ "loss": 0.6753,
538
+ "mean_token_accuracy": 0.8788385137915611,
539
+ "num_tokens": 277527.0,
540
+ "step": 295
541
+ },
542
+ {
543
+ "epoch": 1.0217113665389528,
544
+ "grad_norm": 0.5845906734466553,
545
+ "learning_rate": 0.000131740614334471,
546
+ "loss": 0.5237,
547
+ "mean_token_accuracy": 0.8938747227191925,
548
+ "num_tokens": 282199.0,
549
+ "step": 300
550
+ },
551
+ {
552
+ "epoch": 1.038739889314602,
553
+ "grad_norm": 0.6392928957939148,
554
+ "learning_rate": 0.00013060295790671218,
555
+ "loss": 0.4973,
556
+ "mean_token_accuracy": 0.8982622623443604,
557
+ "num_tokens": 286951.0,
558
+ "step": 305
559
+ },
560
+ {
561
+ "epoch": 1.055768412090251,
562
+ "grad_norm": 0.5399300456047058,
563
+ "learning_rate": 0.00012946530147895337,
564
+ "loss": 0.5076,
565
+ "mean_token_accuracy": 0.9008002370595932,
566
+ "num_tokens": 291569.0,
567
+ "step": 310
568
+ },
569
+ {
570
+ "epoch": 1.0727969348659003,
571
+ "grad_norm": 0.6236026883125305,
572
+ "learning_rate": 0.00012832764505119455,
573
+ "loss": 0.5084,
574
+ "mean_token_accuracy": 0.8972577184438706,
575
+ "num_tokens": 296230.0,
576
+ "step": 315
577
+ },
578
+ {
579
+ "epoch": 1.0898254576415496,
580
+ "grad_norm": 0.7385813593864441,
581
+ "learning_rate": 0.0001271899886234357,
582
+ "loss": 0.5062,
583
+ "mean_token_accuracy": 0.8956585437059402,
584
+ "num_tokens": 301029.0,
585
+ "step": 320
586
+ },
587
+ {
588
+ "epoch": 1.1068539804171988,
589
+ "grad_norm": 0.7647150754928589,
590
+ "learning_rate": 0.00012605233219567692,
591
+ "loss": 0.5078,
592
+ "mean_token_accuracy": 0.8982979074120522,
593
+ "num_tokens": 305696.0,
594
+ "step": 325
595
+ },
596
+ {
597
+ "epoch": 1.123882503192848,
598
+ "grad_norm": 0.6433872580528259,
599
+ "learning_rate": 0.00012491467576791808,
600
+ "loss": 0.5215,
601
+ "mean_token_accuracy": 0.8974734947085381,
602
+ "num_tokens": 310343.0,
603
+ "step": 330
604
+ },
605
+ {
606
+ "epoch": 1.1409110259684971,
607
+ "grad_norm": 0.6470033526420593,
608
+ "learning_rate": 0.0001237770193401593,
609
+ "loss": 0.5261,
610
+ "mean_token_accuracy": 0.8938129872083664,
611
+ "num_tokens": 315097.0,
612
+ "step": 335
613
+ },
614
+ {
615
+ "epoch": 1.1579395487441464,
616
+ "grad_norm": 0.6738846302032471,
617
+ "learning_rate": 0.00012263936291240045,
618
+ "loss": 0.5277,
619
+ "mean_token_accuracy": 0.8924461513757705,
620
+ "num_tokens": 319861.0,
621
+ "step": 340
622
+ },
623
+ {
624
+ "epoch": 1.1749680715197957,
625
+ "grad_norm": 0.6639145016670227,
626
+ "learning_rate": 0.00012150170648464165,
627
+ "loss": 0.5127,
628
+ "mean_token_accuracy": 0.8926685571670532,
629
+ "num_tokens": 324544.0,
630
+ "step": 345
631
+ },
632
+ {
633
+ "epoch": 1.191996594295445,
634
+ "grad_norm": 0.7034420371055603,
635
+ "learning_rate": 0.00012036405005688282,
636
+ "loss": 0.51,
637
+ "mean_token_accuracy": 0.8971043467521668,
638
+ "num_tokens": 329302.0,
639
+ "step": 350
640
+ },
641
+ {
642
+ "epoch": 1.2090251170710942,
643
+ "grad_norm": 0.6675500273704529,
644
+ "learning_rate": 0.000119226393629124,
645
+ "loss": 0.5738,
646
+ "mean_token_accuracy": 0.8855719327926636,
647
+ "num_tokens": 334103.0,
648
+ "step": 355
649
+ },
650
+ {
651
+ "epoch": 1.2260536398467432,
652
+ "grad_norm": 0.6019395589828491,
653
+ "learning_rate": 0.00011808873720136519,
654
+ "loss": 0.476,
655
+ "mean_token_accuracy": 0.8989460453391075,
656
+ "num_tokens": 338666.0,
657
+ "step": 360
658
+ },
659
+ {
660
+ "epoch": 1.2430821626223925,
661
+ "grad_norm": 0.6599250435829163,
662
+ "learning_rate": 0.00011695108077360638,
663
+ "loss": 0.5178,
664
+ "mean_token_accuracy": 0.8887226998805999,
665
+ "num_tokens": 343333.0,
666
+ "step": 365
667
+ },
668
+ {
669
+ "epoch": 1.2601106853980417,
670
+ "grad_norm": 0.7334213852882385,
671
+ "learning_rate": 0.00011581342434584756,
672
+ "loss": 0.5378,
673
+ "mean_token_accuracy": 0.8895460113883018,
674
+ "num_tokens": 348092.0,
675
+ "step": 370
676
+ },
677
+ {
678
+ "epoch": 1.277139208173691,
679
+ "grad_norm": 0.7423357963562012,
680
+ "learning_rate": 0.00011467576791808873,
681
+ "loss": 0.5012,
682
+ "mean_token_accuracy": 0.8994292929768563,
683
+ "num_tokens": 352661.0,
684
+ "step": 375
685
+ },
686
+ {
687
+ "epoch": 1.29416773094934,
688
+ "grad_norm": 0.857515811920166,
689
+ "learning_rate": 0.00011353811149032993,
690
+ "loss": 0.507,
691
+ "mean_token_accuracy": 0.8979884222149849,
692
+ "num_tokens": 357330.0,
693
+ "step": 380
694
+ },
695
+ {
696
+ "epoch": 1.3111962537249893,
697
+ "grad_norm": 0.5656803250312805,
698
+ "learning_rate": 0.0001124004550625711,
699
+ "loss": 0.5009,
700
+ "mean_token_accuracy": 0.8934224143624305,
701
+ "num_tokens": 362020.0,
702
+ "step": 385
703
+ },
704
+ {
705
+ "epoch": 1.3282247765006385,
706
+ "grad_norm": 0.6634964942932129,
707
+ "learning_rate": 0.00011126279863481229,
708
+ "loss": 0.5414,
709
+ "mean_token_accuracy": 0.8910330131649971,
710
+ "num_tokens": 366728.0,
711
+ "step": 390
712
+ },
713
+ {
714
+ "epoch": 1.3452532992762878,
715
+ "grad_norm": 0.7004157304763794,
716
+ "learning_rate": 0.00011012514220705347,
717
+ "loss": 0.4922,
718
+ "mean_token_accuracy": 0.8992783546447753,
719
+ "num_tokens": 371381.0,
720
+ "step": 395
721
+ },
722
+ {
723
+ "epoch": 1.362281822051937,
724
+ "grad_norm": 0.6225594282150269,
725
+ "learning_rate": 0.00010898748577929466,
726
+ "loss": 0.5084,
727
+ "mean_token_accuracy": 0.8956901535391808,
728
+ "num_tokens": 376043.0,
729
+ "step": 400
730
+ },
731
+ {
732
+ "epoch": 1.3793103448275863,
733
+ "grad_norm": 0.8019647598266602,
734
+ "learning_rate": 0.00010784982935153584,
735
+ "loss": 0.5303,
736
+ "mean_token_accuracy": 0.8940754950046539,
737
+ "num_tokens": 380714.0,
738
+ "step": 405
739
+ },
740
+ {
741
+ "epoch": 1.3963388676032356,
742
+ "grad_norm": 0.8314201831817627,
743
+ "learning_rate": 0.00010671217292377703,
744
+ "loss": 0.5249,
745
+ "mean_token_accuracy": 0.8924115225672722,
746
+ "num_tokens": 385498.0,
747
+ "step": 410
748
+ },
749
+ {
750
+ "epoch": 1.4133673903788846,
751
+ "grad_norm": 0.6691393256187439,
752
+ "learning_rate": 0.00010557451649601821,
753
+ "loss": 0.4817,
754
+ "mean_token_accuracy": 0.89882483035326,
755
+ "num_tokens": 390179.0,
756
+ "step": 415
757
+ },
758
+ {
759
+ "epoch": 1.4303959131545338,
760
+ "grad_norm": 0.8554338216781616,
761
+ "learning_rate": 0.00010443686006825938,
762
+ "loss": 0.5191,
763
+ "mean_token_accuracy": 0.8876234069466591,
764
+ "num_tokens": 394930.0,
765
+ "step": 420
766
+ },
767
+ {
768
+ "epoch": 1.447424435930183,
769
+ "grad_norm": 0.696018636226654,
770
+ "learning_rate": 0.00010329920364050057,
771
+ "loss": 0.5386,
772
+ "mean_token_accuracy": 0.891503955423832,
773
+ "num_tokens": 399685.0,
774
+ "step": 425
775
+ },
776
+ {
777
+ "epoch": 1.4644529587058321,
778
+ "grad_norm": 0.7389529943466187,
779
+ "learning_rate": 0.00010216154721274175,
780
+ "loss": 0.4949,
781
+ "mean_token_accuracy": 0.9004919424653053,
782
+ "num_tokens": 404300.0,
783
+ "step": 430
784
+ },
785
+ {
786
+ "epoch": 1.4814814814814814,
787
+ "grad_norm": 1.0227491855621338,
788
+ "learning_rate": 0.00010102389078498294,
789
+ "loss": 0.54,
790
+ "mean_token_accuracy": 0.8893611416220665,
791
+ "num_tokens": 409079.0,
792
+ "step": 435
793
+ },
794
+ {
795
+ "epoch": 1.4985100042571307,
796
+ "grad_norm": 0.6526888012886047,
797
+ "learning_rate": 9.988623435722412e-05,
798
+ "loss": 0.4917,
799
+ "mean_token_accuracy": 0.8958082437515259,
800
+ "num_tokens": 413758.0,
801
+ "step": 440
802
+ },
803
+ {
804
+ "epoch": 1.51553852703278,
805
+ "grad_norm": 0.5875766277313232,
806
+ "learning_rate": 9.874857792946531e-05,
807
+ "loss": 0.4991,
808
+ "mean_token_accuracy": 0.8971148490905761,
809
+ "num_tokens": 418502.0,
810
+ "step": 445
811
+ },
812
+ {
813
+ "epoch": 1.5325670498084292,
814
+ "grad_norm": 0.6892980337142944,
815
+ "learning_rate": 9.761092150170649e-05,
816
+ "loss": 0.4551,
817
+ "mean_token_accuracy": 0.9068983420729637,
818
+ "num_tokens": 423099.0,
819
+ "step": 450
820
+ },
821
+ {
822
+ "epoch": 1.5495955725840784,
823
+ "grad_norm": 0.6264586448669434,
824
+ "learning_rate": 9.647326507394768e-05,
825
+ "loss": 0.468,
826
+ "mean_token_accuracy": 0.9043048679828644,
827
+ "num_tokens": 427701.0,
828
+ "step": 455
829
+ },
830
+ {
831
+ "epoch": 1.5666240953597277,
832
+ "grad_norm": 0.5398015379905701,
833
+ "learning_rate": 9.533560864618886e-05,
834
+ "loss": 0.4877,
835
+ "mean_token_accuracy": 0.8986729174852371,
836
+ "num_tokens": 432430.0,
837
+ "step": 460
838
+ },
839
+ {
840
+ "epoch": 1.5836526181353767,
841
+ "grad_norm": 0.827769935131073,
842
+ "learning_rate": 9.419795221843003e-05,
843
+ "loss": 0.4951,
844
+ "mean_token_accuracy": 0.9012611672282219,
845
+ "num_tokens": 437078.0,
846
+ "step": 465
847
+ },
848
+ {
849
+ "epoch": 1.600681140911026,
850
+ "grad_norm": 0.6888080835342407,
851
+ "learning_rate": 9.306029579067122e-05,
852
+ "loss": 0.5108,
853
+ "mean_token_accuracy": 0.8976602256298065,
854
+ "num_tokens": 441734.0,
855
+ "step": 470
856
+ },
857
+ {
858
+ "epoch": 1.617709663686675,
859
+ "grad_norm": 0.837681233882904,
860
+ "learning_rate": 9.19226393629124e-05,
861
+ "loss": 0.5377,
862
+ "mean_token_accuracy": 0.8850761532783509,
863
+ "num_tokens": 446637.0,
864
+ "step": 475
865
+ },
866
+ {
867
+ "epoch": 1.6347381864623243,
868
+ "grad_norm": 0.7211363315582275,
869
+ "learning_rate": 9.078498293515359e-05,
870
+ "loss": 0.5001,
871
+ "mean_token_accuracy": 0.898733913898468,
872
+ "num_tokens": 451301.0,
873
+ "step": 480
874
+ },
875
+ {
876
+ "epoch": 1.6517667092379735,
877
+ "grad_norm": 0.6663438081741333,
878
+ "learning_rate": 8.964732650739477e-05,
879
+ "loss": 0.5144,
880
+ "mean_token_accuracy": 0.8976200923323632,
881
+ "num_tokens": 455965.0,
882
+ "step": 485
883
+ },
884
+ {
885
+ "epoch": 1.6687952320136228,
886
+ "grad_norm": 0.8935639262199402,
887
+ "learning_rate": 8.850967007963596e-05,
888
+ "loss": 0.5331,
889
+ "mean_token_accuracy": 0.8960411131381989,
890
+ "num_tokens": 460716.0,
891
+ "step": 490
892
+ },
893
+ {
894
+ "epoch": 1.685823754789272,
895
+ "grad_norm": 0.7235546708106995,
896
+ "learning_rate": 8.737201365187714e-05,
897
+ "loss": 0.4831,
898
+ "mean_token_accuracy": 0.8972082689404488,
899
+ "num_tokens": 465370.0,
900
+ "step": 495
901
+ },
902
+ {
903
+ "epoch": 1.7028522775649213,
904
+ "grad_norm": 0.774000346660614,
905
+ "learning_rate": 8.623435722411833e-05,
906
+ "loss": 0.5186,
907
+ "mean_token_accuracy": 0.8950631290674209,
908
+ "num_tokens": 470043.0,
909
+ "step": 500
910
+ },
911
+ {
912
+ "epoch": 1.7198808003405706,
913
+ "grad_norm": 0.5213722586631775,
914
+ "learning_rate": 8.509670079635951e-05,
915
+ "loss": 0.4567,
916
+ "mean_token_accuracy": 0.9016156733036041,
917
+ "num_tokens": 474573.0,
918
+ "step": 505
919
+ },
920
+ {
921
+ "epoch": 1.7369093231162198,
922
+ "grad_norm": 0.7278684377670288,
923
+ "learning_rate": 8.395904436860069e-05,
924
+ "loss": 0.5545,
925
+ "mean_token_accuracy": 0.8925162181258202,
926
+ "num_tokens": 479305.0,
927
+ "step": 510
928
+ },
929
+ {
930
+ "epoch": 1.7539378458918689,
931
+ "grad_norm": 0.7252481579780579,
932
+ "learning_rate": 8.282138794084187e-05,
933
+ "loss": 0.496,
934
+ "mean_token_accuracy": 0.8953201442956924,
935
+ "num_tokens": 484033.0,
936
+ "step": 515
937
+ },
938
+ {
939
+ "epoch": 1.770966368667518,
940
+ "grad_norm": 0.727513313293457,
941
+ "learning_rate": 8.168373151308306e-05,
942
+ "loss": 0.5033,
943
+ "mean_token_accuracy": 0.8998701125383377,
944
+ "num_tokens": 488727.0,
945
+ "step": 520
946
+ },
947
+ {
948
+ "epoch": 1.7879948914431671,
949
+ "grad_norm": 0.5375337600708008,
950
+ "learning_rate": 8.054607508532424e-05,
951
+ "loss": 0.4903,
952
+ "mean_token_accuracy": 0.8960629358887673,
953
+ "num_tokens": 493411.0,
954
+ "step": 525
955
+ },
956
+ {
957
+ "epoch": 1.8050234142188164,
958
+ "grad_norm": 0.5851954221725464,
959
+ "learning_rate": 7.940841865756543e-05,
960
+ "loss": 0.5139,
961
+ "mean_token_accuracy": 0.8972602248191833,
962
+ "num_tokens": 498098.0,
963
+ "step": 530
964
+ },
965
+ {
966
+ "epoch": 1.8220519369944657,
967
+ "grad_norm": 0.6942209005355835,
968
+ "learning_rate": 7.827076222980661e-05,
969
+ "loss": 0.4728,
970
+ "mean_token_accuracy": 0.9009919315576553,
971
+ "num_tokens": 502717.0,
972
+ "step": 535
973
+ },
974
+ {
975
+ "epoch": 1.839080459770115,
976
+ "grad_norm": 0.9342221021652222,
977
+ "learning_rate": 7.71331058020478e-05,
978
+ "loss": 0.5283,
979
+ "mean_token_accuracy": 0.8924958631396294,
980
+ "num_tokens": 507462.0,
981
+ "step": 540
982
+ },
983
+ {
984
+ "epoch": 1.8561089825457642,
985
+ "grad_norm": 0.7415278553962708,
986
+ "learning_rate": 7.599544937428897e-05,
987
+ "loss": 0.5394,
988
+ "mean_token_accuracy": 0.8913042590022087,
989
+ "num_tokens": 512202.0,
990
+ "step": 545
991
+ },
992
+ {
993
+ "epoch": 1.8731375053214134,
994
+ "grad_norm": 0.7223448157310486,
995
+ "learning_rate": 7.485779294653015e-05,
996
+ "loss": 0.5473,
997
+ "mean_token_accuracy": 0.8873603999614715,
998
+ "num_tokens": 517047.0,
999
+ "step": 550
1000
+ },
1001
+ {
1002
+ "epoch": 1.8901660280970627,
1003
+ "grad_norm": 0.6324387192726135,
1004
+ "learning_rate": 7.372013651877134e-05,
1005
+ "loss": 0.4986,
1006
+ "mean_token_accuracy": 0.9018153563141823,
1007
+ "num_tokens": 521653.0,
1008
+ "step": 555
1009
+ },
1010
+ {
1011
+ "epoch": 1.907194550872712,
1012
+ "grad_norm": 0.6177689433097839,
1013
+ "learning_rate": 7.258248009101252e-05,
1014
+ "loss": 0.5242,
1015
+ "mean_token_accuracy": 0.8907949879765511,
1016
+ "num_tokens": 526387.0,
1017
+ "step": 560
1018
+ },
1019
+ {
1020
+ "epoch": 1.924223073648361,
1021
+ "grad_norm": 0.6327561140060425,
1022
+ "learning_rate": 7.14448236632537e-05,
1023
+ "loss": 0.4725,
1024
+ "mean_token_accuracy": 0.9006670027971267,
1025
+ "num_tokens": 531113.0,
1026
+ "step": 565
1027
+ },
1028
+ {
1029
+ "epoch": 1.9412515964240102,
1030
+ "grad_norm": 0.6829894781112671,
1031
+ "learning_rate": 7.030716723549489e-05,
1032
+ "loss": 0.5255,
1033
+ "mean_token_accuracy": 0.8897917374968529,
1034
+ "num_tokens": 535963.0,
1035
+ "step": 570
1036
+ },
1037
+ {
1038
+ "epoch": 1.9582801191996593,
1039
+ "grad_norm": 0.7764301896095276,
1040
+ "learning_rate": 6.916951080773608e-05,
1041
+ "loss": 0.5636,
1042
+ "mean_token_accuracy": 0.8877105817198754,
1043
+ "num_tokens": 540801.0,
1044
+ "step": 575
1045
+ },
1046
+ {
1047
+ "epoch": 1.9753086419753085,
1048
+ "grad_norm": 0.7201740741729736,
1049
+ "learning_rate": 6.803185437997726e-05,
1050
+ "loss": 0.5279,
1051
+ "mean_token_accuracy": 0.8954470381140709,
1052
+ "num_tokens": 545507.0,
1053
+ "step": 580
1054
+ },
1055
+ {
1056
+ "epoch": 1.9923371647509578,
1057
+ "grad_norm": 0.6038010716438293,
1058
+ "learning_rate": 6.689419795221843e-05,
1059
+ "loss": 0.505,
1060
+ "mean_token_accuracy": 0.8970827981829643,
1061
+ "num_tokens": 550257.0,
1062
+ "step": 585
1063
+ },
1064
+ {
1065
+ "epoch": 2.009365687526607,
1066
+ "grad_norm": 0.5724640488624573,
1067
+ "learning_rate": 6.575654152445962e-05,
1068
+ "loss": 0.5361,
1069
+ "mean_token_accuracy": 0.9015150561928749,
1070
+ "num_tokens": 554990.0,
1071
+ "step": 590
1072
+ },
1073
+ {
1074
+ "epoch": 2.0263942103022563,
1075
+ "grad_norm": 0.5974262952804565,
1076
+ "learning_rate": 6.46188850967008e-05,
1077
+ "loss": 0.3674,
1078
+ "mean_token_accuracy": 0.922430993616581,
1079
+ "num_tokens": 559672.0,
1080
+ "step": 595
1081
+ },
1082
+ {
1083
+ "epoch": 2.0434227330779056,
1084
+ "grad_norm": 0.6744574904441833,
1085
+ "learning_rate": 6.348122866894199e-05,
1086
+ "loss": 0.3751,
1087
+ "mean_token_accuracy": 0.9247258752584457,
1088
+ "num_tokens": 564411.0,
1089
+ "step": 600
1090
+ },
1091
+ {
1092
+ "epoch": 2.060451255853555,
1093
+ "grad_norm": 0.7185547351837158,
1094
+ "learning_rate": 6.234357224118317e-05,
1095
+ "loss": 0.3416,
1096
+ "mean_token_accuracy": 0.929543960094452,
1097
+ "num_tokens": 569003.0,
1098
+ "step": 605
1099
+ },
1100
+ {
1101
+ "epoch": 2.077479778629204,
1102
+ "grad_norm": 0.5838123559951782,
1103
+ "learning_rate": 6.120591581342436e-05,
1104
+ "loss": 0.3537,
1105
+ "mean_token_accuracy": 0.930443874001503,
1106
+ "num_tokens": 573739.0,
1107
+ "step": 610
1108
+ },
1109
+ {
1110
+ "epoch": 2.0945083014048533,
1111
+ "grad_norm": 0.8568351864814758,
1112
+ "learning_rate": 6.0068259385665536e-05,
1113
+ "loss": 0.3784,
1114
+ "mean_token_accuracy": 0.9205309540033341,
1115
+ "num_tokens": 578528.0,
1116
+ "step": 615
1117
+ },
1118
+ {
1119
+ "epoch": 2.111536824180502,
1120
+ "grad_norm": 0.5337037444114685,
1121
+ "learning_rate": 5.8930602957906714e-05,
1122
+ "loss": 0.3617,
1123
+ "mean_token_accuracy": 0.9245797485113144,
1124
+ "num_tokens": 583227.0,
1125
+ "step": 620
1126
+ },
1127
+ {
1128
+ "epoch": 2.1285653469561514,
1129
+ "grad_norm": 0.5879887938499451,
1130
+ "learning_rate": 5.77929465301479e-05,
1131
+ "loss": 0.3707,
1132
+ "mean_token_accuracy": 0.9202131152153015,
1133
+ "num_tokens": 587936.0,
1134
+ "step": 625
1135
+ },
1136
+ {
1137
+ "epoch": 2.1455938697318007,
1138
+ "grad_norm": 0.6099004149436951,
1139
+ "learning_rate": 5.665529010238908e-05,
1140
+ "loss": 0.3774,
1141
+ "mean_token_accuracy": 0.9187414139509201,
1142
+ "num_tokens": 592638.0,
1143
+ "step": 630
1144
+ },
1145
+ {
1146
+ "epoch": 2.16262239250745,
1147
+ "grad_norm": 0.6386281251907349,
1148
+ "learning_rate": 5.551763367463026e-05,
1149
+ "loss": 0.3618,
1150
+ "mean_token_accuracy": 0.9270586878061294,
1151
+ "num_tokens": 597181.0,
1152
+ "step": 635
1153
+ },
1154
+ {
1155
+ "epoch": 2.179650915283099,
1156
+ "grad_norm": 0.9021700024604797,
1157
+ "learning_rate": 5.437997724687145e-05,
1158
+ "loss": 0.3585,
1159
+ "mean_token_accuracy": 0.9271015107631684,
1160
+ "num_tokens": 601859.0,
1161
+ "step": 640
1162
+ },
1163
+ {
1164
+ "epoch": 2.1966794380587484,
1165
+ "grad_norm": 0.881395697593689,
1166
+ "learning_rate": 5.324232081911263e-05,
1167
+ "loss": 0.3557,
1168
+ "mean_token_accuracy": 0.9272178143262864,
1169
+ "num_tokens": 606633.0,
1170
+ "step": 645
1171
+ },
1172
+ {
1173
+ "epoch": 2.2137079608343977,
1174
+ "grad_norm": 0.8289951086044312,
1175
+ "learning_rate": 5.210466439135382e-05,
1176
+ "loss": 0.3761,
1177
+ "mean_token_accuracy": 0.9222683504223823,
1178
+ "num_tokens": 611341.0,
1179
+ "step": 650
1180
+ },
1181
+ {
1182
+ "epoch": 2.230736483610047,
1183
+ "grad_norm": 0.7716552019119263,
1184
+ "learning_rate": 5.0967007963594995e-05,
1185
+ "loss": 0.3806,
1186
+ "mean_token_accuracy": 0.9193105801939965,
1187
+ "num_tokens": 616076.0,
1188
+ "step": 655
1189
+ },
1190
+ {
1191
+ "epoch": 2.247765006385696,
1192
+ "grad_norm": 0.7260558605194092,
1193
+ "learning_rate": 4.982935153583618e-05,
1194
+ "loss": 0.3641,
1195
+ "mean_token_accuracy": 0.9221750542521476,
1196
+ "num_tokens": 620729.0,
1197
+ "step": 660
1198
+ },
1199
+ {
1200
+ "epoch": 2.264793529161345,
1201
+ "grad_norm": 0.6313159465789795,
1202
+ "learning_rate": 4.8691695108077365e-05,
1203
+ "loss": 0.3923,
1204
+ "mean_token_accuracy": 0.9229970827698708,
1205
+ "num_tokens": 625451.0,
1206
+ "step": 665
1207
+ },
1208
+ {
1209
+ "epoch": 2.2818220519369943,
1210
+ "grad_norm": 0.6566217541694641,
1211
+ "learning_rate": 4.755403868031855e-05,
1212
+ "loss": 0.3404,
1213
+ "mean_token_accuracy": 0.9257871210575104,
1214
+ "num_tokens": 630049.0,
1215
+ "step": 670
1216
+ },
1217
+ {
1218
+ "epoch": 2.2988505747126435,
1219
+ "grad_norm": 0.8146483302116394,
1220
+ "learning_rate": 4.641638225255973e-05,
1221
+ "loss": 0.3499,
1222
+ "mean_token_accuracy": 0.9254049748182297,
1223
+ "num_tokens": 634646.0,
1224
+ "step": 675
1225
+ },
1226
+ {
1227
+ "epoch": 2.315879097488293,
1228
+ "grad_norm": 0.8177068829536438,
1229
+ "learning_rate": 4.527872582480091e-05,
1230
+ "loss": 0.3662,
1231
+ "mean_token_accuracy": 0.9220140025019645,
1232
+ "num_tokens": 639328.0,
1233
+ "step": 680
1234
+ },
1235
+ {
1236
+ "epoch": 2.332907620263942,
1237
+ "grad_norm": 0.7193973660469055,
1238
+ "learning_rate": 4.41410693970421e-05,
1239
+ "loss": 0.3861,
1240
+ "mean_token_accuracy": 0.9194135531783104,
1241
+ "num_tokens": 644122.0,
1242
+ "step": 685
1243
+ },
1244
+ {
1245
+ "epoch": 2.3499361430395913,
1246
+ "grad_norm": 0.8300774693489075,
1247
+ "learning_rate": 4.300341296928328e-05,
1248
+ "loss": 0.3924,
1249
+ "mean_token_accuracy": 0.9165543273091317,
1250
+ "num_tokens": 648957.0,
1251
+ "step": 690
1252
+ },
1253
+ {
1254
+ "epoch": 2.3669646658152406,
1255
+ "grad_norm": 0.6429705023765564,
1256
+ "learning_rate": 4.186575654152446e-05,
1257
+ "loss": 0.3749,
1258
+ "mean_token_accuracy": 0.922352360188961,
1259
+ "num_tokens": 653645.0,
1260
+ "step": 695
1261
+ },
1262
+ {
1263
+ "epoch": 2.38399318859089,
1264
+ "grad_norm": 0.9316811561584473,
1265
+ "learning_rate": 4.0728100113765646e-05,
1266
+ "loss": 0.3731,
1267
+ "mean_token_accuracy": 0.9198509395122528,
1268
+ "num_tokens": 658472.0,
1269
+ "step": 700
1270
+ },
1271
+ {
1272
+ "epoch": 2.401021711366539,
1273
+ "grad_norm": 0.6092661023139954,
1274
+ "learning_rate": 3.959044368600683e-05,
1275
+ "loss": 0.3614,
1276
+ "mean_token_accuracy": 0.9218982830643654,
1277
+ "num_tokens": 663118.0,
1278
+ "step": 705
1279
+ },
1280
+ {
1281
+ "epoch": 2.4180502341421883,
1282
+ "grad_norm": 0.909447968006134,
1283
+ "learning_rate": 3.8452787258248016e-05,
1284
+ "loss": 0.407,
1285
+ "mean_token_accuracy": 0.9137230664491653,
1286
+ "num_tokens": 668024.0,
1287
+ "step": 710
1288
+ },
1289
+ {
1290
+ "epoch": 2.4350787569178376,
1291
+ "grad_norm": 0.6452695727348328,
1292
+ "learning_rate": 3.7315130830489194e-05,
1293
+ "loss": 0.3642,
1294
+ "mean_token_accuracy": 0.9242654070258141,
1295
+ "num_tokens": 672593.0,
1296
+ "step": 715
1297
+ },
1298
+ {
1299
+ "epoch": 2.4521072796934864,
1300
+ "grad_norm": 0.7429100275039673,
1301
+ "learning_rate": 3.617747440273038e-05,
1302
+ "loss": 0.3762,
1303
+ "mean_token_accuracy": 0.9200442656874657,
1304
+ "num_tokens": 677246.0,
1305
+ "step": 720
1306
+ },
1307
+ {
1308
+ "epoch": 2.4691358024691357,
1309
+ "grad_norm": 0.6262103319168091,
1310
+ "learning_rate": 3.5039817974971564e-05,
1311
+ "loss": 0.3631,
1312
+ "mean_token_accuracy": 0.9242240786552429,
1313
+ "num_tokens": 681899.0,
1314
+ "step": 725
1315
+ },
1316
+ {
1317
+ "epoch": 2.486164325244785,
1318
+ "grad_norm": 0.7170459032058716,
1319
+ "learning_rate": 3.390216154721274e-05,
1320
+ "loss": 0.3518,
1321
+ "mean_token_accuracy": 0.9257205232977868,
1322
+ "num_tokens": 686559.0,
1323
+ "step": 730
1324
+ },
1325
+ {
1326
+ "epoch": 2.503192848020434,
1327
+ "grad_norm": 0.7899272441864014,
1328
+ "learning_rate": 3.276450511945393e-05,
1329
+ "loss": 0.3408,
1330
+ "mean_token_accuracy": 0.927695432305336,
1331
+ "num_tokens": 691193.0,
1332
+ "step": 735
1333
+ },
1334
+ {
1335
+ "epoch": 2.5202213707960834,
1336
+ "grad_norm": 0.8176191449165344,
1337
+ "learning_rate": 3.162684869169511e-05,
1338
+ "loss": 0.3554,
1339
+ "mean_token_accuracy": 0.9244274586439133,
1340
+ "num_tokens": 695862.0,
1341
+ "step": 740
1342
+ },
1343
+ {
1344
+ "epoch": 2.5372498935717327,
1345
+ "grad_norm": 0.9307223558425903,
1346
+ "learning_rate": 3.0489192263936294e-05,
1347
+ "loss": 0.3762,
1348
+ "mean_token_accuracy": 0.9196016103029251,
1349
+ "num_tokens": 700732.0,
1350
+ "step": 745
1351
+ },
1352
+ {
1353
+ "epoch": 2.554278416347382,
1354
+ "grad_norm": 0.7519947290420532,
1355
+ "learning_rate": 2.9351535836177476e-05,
1356
+ "loss": 0.37,
1357
+ "mean_token_accuracy": 0.9214758723974228,
1358
+ "num_tokens": 705428.0,
1359
+ "step": 750
1360
+ },
1361
+ {
1362
+ "epoch": 2.571306939123031,
1363
+ "grad_norm": 0.7623237371444702,
1364
+ "learning_rate": 2.8213879408418657e-05,
1365
+ "loss": 0.3496,
1366
+ "mean_token_accuracy": 0.9245725467801094,
1367
+ "num_tokens": 710035.0,
1368
+ "step": 755
1369
+ },
1370
+ {
1371
+ "epoch": 2.58833546189868,
1372
+ "grad_norm": 0.6571420431137085,
1373
+ "learning_rate": 2.7076222980659842e-05,
1374
+ "loss": 0.3662,
1375
+ "mean_token_accuracy": 0.9226716786623002,
1376
+ "num_tokens": 714753.0,
1377
+ "step": 760
1378
+ },
1379
+ {
1380
+ "epoch": 2.6053639846743293,
1381
+ "grad_norm": 0.6745423078536987,
1382
+ "learning_rate": 2.5938566552901024e-05,
1383
+ "loss": 0.3672,
1384
+ "mean_token_accuracy": 0.9193284913897515,
1385
+ "num_tokens": 719410.0,
1386
+ "step": 765
1387
+ },
1388
+ {
1389
+ "epoch": 2.6223925074499785,
1390
+ "grad_norm": 0.9500595927238464,
1391
+ "learning_rate": 2.480091012514221e-05,
1392
+ "loss": 0.3729,
1393
+ "mean_token_accuracy": 0.9209223091602325,
1394
+ "num_tokens": 724210.0,
1395
+ "step": 770
1396
+ },
1397
+ {
1398
+ "epoch": 2.639421030225628,
1399
+ "grad_norm": 0.6964495182037354,
1400
+ "learning_rate": 2.366325369738339e-05,
1401
+ "loss": 0.3505,
1402
+ "mean_token_accuracy": 0.9281451672315597,
1403
+ "num_tokens": 728969.0,
1404
+ "step": 775
1405
+ },
1406
+ {
1407
+ "epoch": 2.656449553001277,
1408
+ "grad_norm": 0.868914008140564,
1409
+ "learning_rate": 2.2525597269624575e-05,
1410
+ "loss": 0.3709,
1411
+ "mean_token_accuracy": 0.9212313622236252,
1412
+ "num_tokens": 733797.0,
1413
+ "step": 780
1414
+ },
1415
+ {
1416
+ "epoch": 2.6734780757769263,
1417
+ "grad_norm": 0.7551370859146118,
1418
+ "learning_rate": 2.138794084186576e-05,
1419
+ "loss": 0.367,
1420
+ "mean_token_accuracy": 0.9220638558268547,
1421
+ "num_tokens": 738487.0,
1422
+ "step": 785
1423
+ },
1424
+ {
1425
+ "epoch": 2.6905065985525756,
1426
+ "grad_norm": 0.7959733009338379,
1427
+ "learning_rate": 2.025028441410694e-05,
1428
+ "loss": 0.3634,
1429
+ "mean_token_accuracy": 0.9227283328771592,
1430
+ "num_tokens": 743145.0,
1431
+ "step": 790
1432
+ },
1433
+ {
1434
+ "epoch": 2.707535121328225,
1435
+ "grad_norm": 0.8846186399459839,
1436
+ "learning_rate": 1.9112627986348127e-05,
1437
+ "loss": 0.3595,
1438
+ "mean_token_accuracy": 0.9253345713019371,
1439
+ "num_tokens": 747814.0,
1440
+ "step": 795
1441
+ },
1442
+ {
1443
+ "epoch": 2.724563644103874,
1444
+ "grad_norm": 0.6306168437004089,
1445
+ "learning_rate": 1.7974971558589308e-05,
1446
+ "loss": 0.3507,
1447
+ "mean_token_accuracy": 0.924257718026638,
1448
+ "num_tokens": 752477.0,
1449
+ "step": 800
1450
+ }
1451
+ ],
1452
+ "logging_steps": 5,
1453
+ "max_steps": 879,
1454
+ "num_input_tokens_seen": 0,
1455
+ "num_train_epochs": 3,
1456
+ "save_steps": 200,
1457
+ "stateful_callbacks": {
1458
+ "TrainerControl": {
1459
+ "args": {
1460
+ "should_epoch_stop": false,
1461
+ "should_evaluate": false,
1462
+ "should_log": false,
1463
+ "should_save": true,
1464
+ "should_training_stop": false
1465
+ },
1466
+ "attributes": {}
1467
+ }
1468
+ },
1469
+ "total_flos": 3.4073066251935744e+16,
1470
+ "train_batch_size": 1,
1471
+ "trial_name": null,
1472
+ "trial_params": null
1473
+ }
checkpoint-800/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc4e07dc6df6129e6d2045027becfa7300f4a8ae9e98a02f1c9d1066e93703ce
3
+ size 5624
checkpoint-879/README.md ADDED
@@ -0,0 +1,209 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: NousResearch/Hermes-3-Llama-3.1-8B
3
+ library_name: peft
4
+ pipeline_tag: text-generation
5
+ tags:
6
+ - base_model:adapter:NousResearch/Hermes-3-Llama-3.1-8B
7
+ - lora
8
+ - sft
9
+ - transformers
10
+ - trl
11
+ ---
12
+
13
+ # Model Card for Model ID
14
+
15
+ <!-- Provide a quick summary of what the model is/does. -->
16
+
17
+
18
+
19
+ ## Model Details
20
+
21
+ ### Model Description
22
+
23
+ <!-- Provide a longer summary of what this model is. -->
24
+
25
+
26
+
27
+ - **Developed by:** [More Information Needed]
28
+ - **Funded by [optional]:** [More Information Needed]
29
+ - **Shared by [optional]:** [More Information Needed]
30
+ - **Model type:** [More Information Needed]
31
+ - **Language(s) (NLP):** [More Information Needed]
32
+ - **License:** [More Information Needed]
33
+ - **Finetuned from model [optional]:** [More Information Needed]
34
+
35
+ ### Model Sources [optional]
36
+
37
+ <!-- Provide the basic links for the model. -->
38
+
39
+ - **Repository:** [More Information Needed]
40
+ - **Paper [optional]:** [More Information Needed]
41
+ - **Demo [optional]:** [More Information Needed]
42
+
43
+ ## Uses
44
+
45
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
46
+
47
+ ### Direct Use
48
+
49
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
50
+
51
+ [More Information Needed]
52
+
53
+ ### Downstream Use [optional]
54
+
55
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
56
+
57
+ [More Information Needed]
58
+
59
+ ### Out-of-Scope Use
60
+
61
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
62
+
63
+ [More Information Needed]
64
+
65
+ ## Bias, Risks, and Limitations
66
+
67
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
68
+
69
+ [More Information Needed]
70
+
71
+ ### Recommendations
72
+
73
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
74
+
75
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
76
+
77
+ ## How to Get Started with the Model
78
+
79
+ Use the code below to get started with the model.
80
+
81
+ [More Information Needed]
82
+
83
+ ## Training Details
84
+
85
+ ### Training Data
86
+
87
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
88
+
89
+ [More Information Needed]
90
+
91
+ ### Training Procedure
92
+
93
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
94
+
95
+ #### Preprocessing [optional]
96
+
97
+ [More Information Needed]
98
+
99
+
100
+ #### Training Hyperparameters
101
+
102
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
103
+
104
+ #### Speeds, Sizes, Times [optional]
105
+
106
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
107
+
108
+ [More Information Needed]
109
+
110
+ ## Evaluation
111
+
112
+ <!-- This section describes the evaluation protocols and provides the results. -->
113
+
114
+ ### Testing Data, Factors & Metrics
115
+
116
+ #### Testing Data
117
+
118
+ <!-- This should link to a Dataset Card if possible. -->
119
+
120
+ [More Information Needed]
121
+
122
+ #### Factors
123
+
124
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
125
+
126
+ [More Information Needed]
127
+
128
+ #### Metrics
129
+
130
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
131
+
132
+ [More Information Needed]
133
+
134
+ ### Results
135
+
136
+ [More Information Needed]
137
+
138
+ #### Summary
139
+
140
+
141
+
142
+ ## Model Examination [optional]
143
+
144
+ <!-- Relevant interpretability work for the model goes here -->
145
+
146
+ [More Information Needed]
147
+
148
+ ## Environmental Impact
149
+
150
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
151
+
152
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
153
+
154
+ - **Hardware Type:** [More Information Needed]
155
+ - **Hours used:** [More Information Needed]
156
+ - **Cloud Provider:** [More Information Needed]
157
+ - **Compute Region:** [More Information Needed]
158
+ - **Carbon Emitted:** [More Information Needed]
159
+
160
+ ## Technical Specifications [optional]
161
+
162
+ ### Model Architecture and Objective
163
+
164
+ [More Information Needed]
165
+
166
+ ### Compute Infrastructure
167
+
168
+ [More Information Needed]
169
+
170
+ #### Hardware
171
+
172
+ [More Information Needed]
173
+
174
+ #### Software
175
+
176
+ [More Information Needed]
177
+
178
+ ## Citation [optional]
179
+
180
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
181
+
182
+ **BibTeX:**
183
+
184
+ [More Information Needed]
185
+
186
+ **APA:**
187
+
188
+ [More Information Needed]
189
+
190
+ ## Glossary [optional]
191
+
192
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
193
+
194
+ [More Information Needed]
195
+
196
+ ## More Information [optional]
197
+
198
+ [More Information Needed]
199
+
200
+ ## Model Card Authors [optional]
201
+
202
+ [More Information Needed]
203
+
204
+ ## Model Card Contact
205
+
206
+ [More Information Needed]
207
+ ### Framework versions
208
+
209
+ - PEFT 0.20.0
checkpoint-879/adapter_config.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alora_invocation_tokens": null,
3
+ "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": null,
6
+ "base_model_name_or_path": "NousResearch/Hermes-3-Llama-3.1-8B",
7
+ "bias": "none",
8
+ "corda_config": null,
9
+ "ensure_weight_tying": false,
10
+ "eva_config": null,
11
+ "exclude_modules": null,
12
+ "fan_in_fan_out": false,
13
+ "inference_mode": true,
14
+ "init_lora_weights": true,
15
+ "layer_replication": null,
16
+ "layers_pattern": null,
17
+ "layers_to_transform": null,
18
+ "loftq_config": {},
19
+ "lora_alpha": 32,
20
+ "lora_bias": false,
21
+ "lora_dropout": 0.05,
22
+ "lora_ga_config": null,
23
+ "megatron_config": null,
24
+ "megatron_core": "megatron.core",
25
+ "modules_to_save": null,
26
+ "monteclora_config": null,
27
+ "peft_type": "LORA",
28
+ "peft_version": "0.20.0",
29
+ "qalora_group_size": 16,
30
+ "r": 16,
31
+ "rank_pattern": {},
32
+ "revision": null,
33
+ "target_modules": [
34
+ "v_proj",
35
+ "q_proj",
36
+ "k_proj",
37
+ "down_proj",
38
+ "up_proj",
39
+ "gate_proj",
40
+ "o_proj"
41
+ ],
42
+ "target_parameters": null,
43
+ "task_type": "CAUSAL_LM",
44
+ "trainable_token_indices": null,
45
+ "use_bdlora": null,
46
+ "use_dora": false,
47
+ "use_qalora": false,
48
+ "use_rslora": false,
49
+ "velora_config": null
50
+ }